[
  {
    "baseline": false,
    "candidate": "claude-opus-4-8",
    "candidate_sha256": "6502df071a3d868a16c3ff942864129f7a89a61361d4ed95aee773c3383db926",
    "checkpoints_count": 59,
    "graded_at": "2026-05-30T03:46:56Z",
    "label": "Claude Opus 4.8",
    "model": "claude-opus-4-8",
    "overall": 0.7090450062635527,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "bulletgba-gameplay": {
        "audio_score": 0.9650147662567736,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9952475791544172
      },
      "celeste-gameplay": {
        "audio_score": 0.8454558928828791,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.4025215488954425
      },
      "chip-advance-gameplay": {
        "audio_score": 0.60340208233347,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.954359359090322
      },
      "collie-defense-gameplay": {
        "audio_score": 0.9134098100454228,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9982429903823256
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 1.0
      },
      "goodboy-gameplay": {
        "audio_score": 0.9388231869252824,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9617640413869278
      },
      "heartwrench-gameplay": {
        "audio_score": 0.5953268755100382,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.849843543555548
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 1.0
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 0.00004148725678240887
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 4.0143404553356466e-7
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 0.000017382629367735252
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "piugba-gameplay": {
        "audio_score": 0.6134799985556686,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9638859409437254
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 1.4636172764406895e-14
      },
      "spout-gameplay": {
        "audio_score": 0.21585520598011332,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.2957476727346407
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 2.7561764841325496e-15
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 5.628097565437776e-13
      },
      "tonc-snd1": {
        "audio_score": 0.6801946403013801,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.916508013118264
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.30440701760125793,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.2479958119527396
      },
      "waimanu-gameplay": {
        "audio_score": 0.8843331196926391,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9277940633373498
      }
    },
    "provider": "Anthropic",
    "sections": {
      "audio": {
        "score": 0.6906075769285213,
        "subsystems": {
          "game_audio": 0.7394167925396175,
          "psg": 0.6417983613174251
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 0.5326418458751416,
        "subsystems": {
          "cpu": 0.8888908202921519,
          "dma": 0.5000207436283912,
          "halt_irq": 1.4636172764406895e-14,
          "memory": 0.5000002007170228,
          "timer": 2.827829665139551e-13
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.7739918695047002,
        "subsystems": {
          "gameplay": 0.7739918695047002
        },
        "weight": 0.6
      }
    },
    "tokens_used": 57080000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 3,
        "commit_sha": "82c41c1925540658fecf9c7cdd9166107b944084",
        "kind": "auto-save",
        "overall": 0.6318910292812278,
        "overall_raw": 0.6318910292812278,
        "tokens": 395000,
        "wall_clock_hours": 0.7666666666666667
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "09cbb5524ebc210fd224f8908c76873261fcd7f9",
        "kind": "auto-save",
        "overall": 0.6008506473040448,
        "overall_raw": 0.6008506473040448,
        "tokens": 507000,
        "wall_clock_hours": 1.0166666666666666
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "f78b65169e39da53599dbc5a19e0f05b2e929e40",
        "kind": "auto-save",
        "overall": 0.6034313485424273,
        "overall_raw": 0.6034313485424273,
        "tokens": 598000,
        "wall_clock_hours": 1.2666666666666666
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "26806639086c674b554529e109ca004b628f9539",
        "kind": "auto-save",
        "overall": 0.6062238201675453,
        "overall_raw": 0.6062238201675453,
        "tokens": 645000,
        "wall_clock_hours": 1.5166666666666666
      },
      {
        "checkpoint_id": 7,
        "commit_sha": "2bd5e57c974bff5d46b2f395a30cabc0057b3dad",
        "kind": "auto-save",
        "overall": 0.5903542406351281,
        "overall_raw": 0.5903542406351281,
        "tokens": 757000,
        "wall_clock_hours": 1.7666666666666666
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "12e89e409fb28c4f45764b07382b3525711aff00",
        "kind": "auto-save",
        "overall": 0.5903446287052976,
        "overall_raw": 0.5903446287052976,
        "tokens": 845000,
        "wall_clock_hours": 2.0166666666666666
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "fb0186e8e9650920ac977cd3794c3736837f8590",
        "kind": "auto-save",
        "overall": 0.5917386726958328,
        "overall_raw": 0.5917386726958328,
        "tokens": 901000,
        "wall_clock_hours": 2.2666666666666666
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "72b2279e472ef2f8450df8b009ee7ea6de5f6806",
        "kind": "auto-save",
        "overall": 0.6048289552551345,
        "overall_raw": 0.6048289552551345,
        "tokens": 964000,
        "wall_clock_hours": 2.5166666666666666
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "defa6385b77c1399ddf818c02d698520fa7237ce",
        "kind": "auto-save",
        "overall": 0.6619000391707798,
        "overall_raw": 0.6619000391707798,
        "tokens": 1040000,
        "wall_clock_hours": 2.7666666666666666
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "8695327c8eb34237d29e62215f9204e804a20ced",
        "kind": "auto-save",
        "overall": 0.6917795756223298,
        "overall_raw": 0.6917795756223298,
        "tokens": 1120000,
        "wall_clock_hours": 3.0166666666666666
      },
      {
        "checkpoint_id": 13,
        "commit_sha": "160b3af8f038d7c930281ce1a32da552d78826d1",
        "kind": "auto-save",
        "overall": 0.6919289833075803,
        "overall_raw": 0.6919289833075803,
        "tokens": 1210000,
        "wall_clock_hours": 3.2666666666666666
      },
      {
        "checkpoint_id": 14,
        "commit_sha": "c3f5675949cd6000f90157501e4936493799b1fc",
        "kind": "auto-save",
        "overall": 0.6919289833075803,
        "overall_raw": 0.6919289833075803,
        "tokens": 1280000,
        "wall_clock_hours": 3.5166666666666666
      },
      {
        "checkpoint_id": 15,
        "commit_sha": "00715bcfe9250c7cf894b9c2767e2d789c49812a",
        "kind": "auto-save",
        "overall": 0.6919289833075803,
        "overall_raw": 0.6919289833075803,
        "tokens": 1350000,
        "wall_clock_hours": 3.7666666666666666
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "ac5fd6e1d173082465bc196e29b0053fb50ebd23",
        "kind": "auto-save",
        "overall": 0.6664583389862028,
        "overall_raw": 0.6664583389862028,
        "tokens": 1480000,
        "wall_clock_hours": 4.266666666666667
      },
      {
        "checkpoint_id": 17,
        "commit_sha": "326511c4720069775794acdf241afd6abe14b700",
        "kind": "auto-save",
        "overall": 0.6665078557593,
        "overall_raw": 0.6665078557593,
        "tokens": 2660000,
        "wall_clock_hours": 5.25
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "5c631018c5da4aa80a796728b32a75d604335b38",
        "kind": "auto-save",
        "overall": 0.6665015850951894,
        "overall_raw": 0.6665015850951894,
        "tokens": 2710000,
        "wall_clock_hours": 5.5
      },
      {
        "checkpoint_id": 19,
        "commit_sha": "a2f2b7522b3f384654d9a923ee1a93eb160e842c",
        "kind": "auto-save",
        "overall": 0.674018823878939,
        "overall_raw": 0.674018823878939,
        "tokens": 2860000,
        "wall_clock_hours": 5.766666666666667
      },
      {
        "checkpoint_id": 20,
        "commit_sha": "513c7fdb3cbda0bff9502ea5d6339c8ca8346888",
        "kind": "auto-save",
        "overall": 0.6902727113177962,
        "overall_raw": 0.6902727113177962,
        "tokens": 2920000,
        "wall_clock_hours": 6.016666666666667
      },
      {
        "checkpoint_id": 21,
        "commit_sha": "1aedcf61e842fbd7bc1b8cac109b50667a52bf77",
        "kind": "auto-save",
        "overall": 0.6902727113177962,
        "overall_raw": 0.6902727113177962,
        "tokens": 3320000,
        "wall_clock_hours": 6.516666666666667
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "7909f1ddfb646c837f821267632e0d34206514f2",
        "kind": "auto-save",
        "overall": 0.6902727113177962,
        "overall_raw": 0.6902727113177962,
        "tokens": 3390000,
        "wall_clock_hours": 6.766666666666667
      },
      {
        "checkpoint_id": 23,
        "commit_sha": "287faa597632353a91d975805eb66e3fcd0631b8",
        "kind": "auto-save",
        "overall": 0.6728214380896101,
        "overall_raw": 0.6728214380896101,
        "tokens": 3510000,
        "wall_clock_hours": 7.016666666666667
      },
      {
        "checkpoint_id": 24,
        "commit_sha": "feb41a0bc5310b1d997f941e1088d3d71f8ad839",
        "kind": "auto-save",
        "overall": 0.6652455851295757,
        "overall_raw": 0.6652455851295757,
        "tokens": 3640000,
        "wall_clock_hours": 7.266666666666667
      },
      {
        "checkpoint_id": 25,
        "commit_sha": "defd6cc6ea53abc6bc23cf669aa0c9470a47a180",
        "kind": "auto-save",
        "overall": 0.6542821265987802,
        "overall_raw": 0.6542821265987802,
        "tokens": 4440000,
        "wall_clock_hours": 8.016666666666667
      },
      {
        "checkpoint_id": 26,
        "commit_sha": "fa8b41972a4d20a383ae7ab2c84ebf4954efab4a",
        "kind": "auto-save",
        "overall": 0.6709095752564986,
        "overall_raw": 0.6709095752564986,
        "tokens": 5140000,
        "wall_clock_hours": 8.266666666666667
      },
      {
        "checkpoint_id": 27,
        "commit_sha": "504c1cc14252714b67ab76bf87db95427bf49784",
        "kind": "auto-save",
        "overall": 0.6902727113177962,
        "overall_raw": 0.6902727113177962,
        "tokens": 6670000,
        "wall_clock_hours": 8.783333333333333
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "c7c37e517dbc587de3972eccd9662defda17fc36",
        "kind": "auto-save",
        "overall": 0.6902727113177962,
        "overall_raw": 0.6902727113177962,
        "tokens": 6790000,
        "wall_clock_hours": 9.033333333333333
      },
      {
        "checkpoint_id": 29,
        "commit_sha": "953cbf6415d2268aa31e51fd61bd0ebd892aa552",
        "kind": "auto-save",
        "overall": 0.6902726178483656,
        "overall_raw": 0.6902726178483656,
        "tokens": 8760000,
        "wall_clock_hours": 9.516666666666667
      },
      {
        "checkpoint_id": 30,
        "commit_sha": "f288841327d8543c76aff5188c99cca12b33588d",
        "kind": "auto-save",
        "overall": 0.6902726178483656,
        "overall_raw": 0.6902726178483656,
        "tokens": 9810000,
        "wall_clock_hours": 9.766666666666667
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "dc4e26dbffd669a1beb2bf30b4864dc490e3a8ab",
        "kind": "auto-save",
        "overall": 0.6903896933095105,
        "overall_raw": 0.6903896933095105,
        "tokens": 10700000,
        "wall_clock_hours": 10.266666666666667
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "d2c1c45bcae3cfe106fb1ab3fb7dcd08510a4083",
        "kind": "auto-save",
        "overall": 0.690400262479675,
        "overall_raw": 0.690400262479675,
        "tokens": 11290000,
        "wall_clock_hours": 10.516666666666667
      },
      {
        "checkpoint_id": 33,
        "commit_sha": "27cfc4051540f50afd99aaff65e61c33df01f8d7",
        "kind": "auto-save",
        "overall": 0.7031778689907278,
        "overall_raw": 0.7031778689907278,
        "tokens": 12070000,
        "wall_clock_hours": 11.033333333333333
      },
      {
        "checkpoint_id": 34,
        "commit_sha": "a3b3d0c6bf66a7da488595e2e4301c7c03a23f00",
        "kind": "auto-save",
        "overall": 0.7031802425302908,
        "overall_raw": 0.7031802425302908,
        "tokens": 15310000,
        "wall_clock_hours": 11.766666666666667
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "ab92590eedf2dd4b54a77815fdd86b2f532d4633",
        "kind": "auto-save",
        "overall": 0.7031802425302908,
        "overall_raw": 0.7031802425302908,
        "tokens": 15450000,
        "wall_clock_hours": 12.016666666666667
      },
      {
        "checkpoint_id": 36,
        "commit_sha": "48327e6510e8740497d8f32d1cc4f806d05ecc8c",
        "kind": "auto-save",
        "overall": 0.7031802425302908,
        "overall_raw": 0.7031802425302908,
        "tokens": 17350000,
        "wall_clock_hours": 12.266666666666667
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "27fbdf804fc14b785fb4749db32039c8a7fa7bbd",
        "kind": "auto-save",
        "overall": 0.7031802425302908,
        "overall_raw": 0.7031802425302908,
        "tokens": 18580000,
        "wall_clock_hours": 12.516666666666667
      },
      {
        "checkpoint_id": 38,
        "commit_sha": "b96c6e83a4d39cee91b6c4774596987c19374c6f",
        "kind": "auto-save",
        "overall": 0.7031802425302908,
        "overall_raw": 0.7031802425302908,
        "tokens": 19110000,
        "wall_clock_hours": 13.033333333333333
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "2337e4effe572da228196bd3cf11bded57a50430",
        "kind": "auto-save",
        "overall": 0.7031802425302908,
        "overall_raw": 0.7031802425302908,
        "tokens": 19860000,
        "wall_clock_hours": 13.283333333333333
      },
      {
        "checkpoint_id": 40,
        "commit_sha": "1672f3fb4a356f7000c7e8765a92b4d546695378",
        "kind": "auto-save",
        "overall": 0.7031802425302908,
        "overall_raw": 0.7031802425302908,
        "tokens": 20370000,
        "wall_clock_hours": 13.533333333333333
      },
      {
        "checkpoint_id": 42,
        "commit_sha": "221d582e18a24cfee6cb4055fea3eacdb69139a9",
        "kind": "auto-save",
        "overall": 0.7086098747676647,
        "overall_raw": 0.7086098747676647,
        "tokens": 21070000,
        "wall_clock_hours": 14.016666666666667
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "43ab24d8c125ec6b81e253f6a1db0c5d81361a6a",
        "kind": "auto-save",
        "overall": 0.7086098842793924,
        "overall_raw": 0.7086098842793924,
        "tokens": 23300000,
        "wall_clock_hours": 14.783333333333333
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "07a01fa4d0ae76bdf9cf78c6022be6e0ab722c08",
        "kind": "auto-save",
        "overall": 0.7086098842793924,
        "overall_raw": 0.7086098842793924,
        "tokens": 24150000,
        "wall_clock_hours": 15.033333333333333
      },
      {
        "checkpoint_id": 46,
        "commit_sha": "9783e7a778858b327130f5740dcbc004918146c7",
        "kind": "auto-save",
        "overall": 0.7090291181990283,
        "overall_raw": 0.7090291181990283,
        "tokens": 26000000,
        "wall_clock_hours": 16.033333333333335
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "0a601f74b94db12bff53a1427f9283491c6894f4",
        "kind": "auto-save",
        "overall": 0.7090291181990283,
        "overall_raw": 0.7090291181990283,
        "tokens": 26500000,
        "wall_clock_hours": 16.283333333333335
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "394db39c1e18c6cfe759dde02b0bee479e0b2950",
        "kind": "auto-save",
        "overall": 0.7090291181990283,
        "overall_raw": 0.7090291181990283,
        "tokens": 27010000,
        "wall_clock_hours": 16.533333333333335
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "b0302ffa2e7780741e19d1bd977334a70c3ff678",
        "kind": "auto-save",
        "overall": 0.7090291181990283,
        "overall_raw": 0.7090291181990283,
        "tokens": 28010000,
        "wall_clock_hours": 16.766666666666666
      },
      {
        "checkpoint_id": 50,
        "commit_sha": "3af94d29b4eec6fa75ffd4ee2f557f67d03a6413",
        "kind": "auto-save",
        "overall": 0.7090291181990283,
        "overall_raw": 0.7090291181990283,
        "tokens": 29140000,
        "wall_clock_hours": 17.033333333333335
      },
      {
        "checkpoint_id": 51,
        "commit_sha": "505ed8b9a53eab42f7a1f7837d82bbdf80241775",
        "kind": "auto-save",
        "overall": 0.7090290621676876,
        "overall_raw": 0.7090290621676876,
        "tokens": 31800000,
        "wall_clock_hours": 17.55
      },
      {
        "checkpoint_id": 52,
        "commit_sha": "5b6b88ef57ee3fc1610d3e3fed0554d0d624e25f",
        "kind": "auto-save",
        "overall": 0.7090290621676876,
        "overall_raw": 0.7090290621676876,
        "tokens": 32659999,
        "wall_clock_hours": 17.8
      },
      {
        "checkpoint_id": 53,
        "commit_sha": "a07698d6ebc1bf36fae2eec65c8a52931600aa91",
        "kind": "auto-save",
        "overall": 0.7090290621676876,
        "overall_raw": 0.7090290621676876,
        "tokens": 36160000,
        "wall_clock_hours": 18.283333333333335
      },
      {
        "checkpoint_id": 54,
        "commit_sha": "3dda39c591d5496f52dcf6f7605bcacb2e9f5dc9",
        "kind": "auto-save",
        "overall": 0.7090290621676876,
        "overall_raw": 0.7090290621676876,
        "tokens": 37210000,
        "wall_clock_hours": 18.533333333333335
      },
      {
        "checkpoint_id": 55,
        "commit_sha": "a553affc0bd76bf62af182977ee0309e0ec1d028",
        "kind": "auto-save",
        "overall": 0.7090290621676876,
        "overall_raw": 0.7090290621676876,
        "tokens": 38340000,
        "wall_clock_hours": 18.8
      },
      {
        "checkpoint_id": 56,
        "commit_sha": "6514dda008344c3b70463b6bd333f73d7e474a9d",
        "kind": "auto-save",
        "overall": 0.7090290621676876,
        "overall_raw": 0.7090290621676876,
        "tokens": 38810000,
        "wall_clock_hours": 19.533333333333335
      },
      {
        "checkpoint_id": 57,
        "commit_sha": "ca978024a2466108dc38e6a45fb4cac8c04158c2",
        "kind": "auto-save",
        "overall": 0.7090290621676876,
        "overall_raw": 0.7090290621676876,
        "tokens": 39540000,
        "wall_clock_hours": 20.05
      },
      {
        "checkpoint_id": 58,
        "commit_sha": "537827bcb20b4a54fd882467be9804ff23eabc2b",
        "kind": "auto-save",
        "overall": 0.7090290432951908,
        "overall_raw": 0.7090290432951908,
        "tokens": 40940000,
        "wall_clock_hours": 20.8
      },
      {
        "checkpoint_id": 59,
        "commit_sha": "716546f336aec5a54d3c6901de28b2456028c868",
        "kind": "auto-save",
        "overall": 0.7090450062635527,
        "overall_raw": 0.7090450062635527,
        "tokens": 49500000,
        "wall_clock_hours": 22.8
      },
      {
        "checkpoint_id": 60,
        "commit_sha": "a7e8e03cdefb6f7bc61a0e407b028aee5d890309",
        "kind": "auto-save",
        "overall": 0.7090450062635527,
        "overall_raw": 0.7090450062635527,
        "tokens": 53030000,
        "wall_clock_hours": 23.3
      },
      {
        "checkpoint_id": 61,
        "commit_sha": "412cb8c5c00f6a5a8151396669326fc79fac088a",
        "kind": "auto-save",
        "overall": 0.7090450062635527,
        "overall_raw": 0.7090450062635527,
        "tokens": 53060000,
        "wall_clock_hours": 23.55
      },
      {
        "checkpoint_id": 62,
        "commit_sha": "710197e5636da5306cfc68f67cedf59e12c26979",
        "kind": "auto-save",
        "overall": 0.7090450062635527,
        "overall_raw": 0.7090450062635527,
        "tokens": 57080000,
        "wall_clock_hours": 24.15
      },
      {
        "checkpoint_id": 63,
        "commit_sha": "b4cc64417d0aeb41607d1a181f1072b352ae76cd",
        "kind": "auto-save",
        "overall": 0.7090450062635527,
        "overall_raw": 0.7090450062635527,
        "tokens": 57080000,
        "wall_clock_hours": 24.15
      }
    ],
    "wall_clock_hours": 24.15
  },
  {
    "baseline": false,
    "candidate": "gpt-5-5",
    "candidate_sha256": "d7f94391a282d6e9213d497d53b853484ae9215cca242a077ad1b8619714f2b0",
    "checkpoints_count": 70,
    "graded_at": "2026-05-03T08:40:21Z",
    "has_wasm": true,
    "label": "GPT-5.5",
    "model": "gpt-5.5",
    "overall": 0.5322037178151383,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 8.12294043132762e-10
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.984762405107098e-11
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "bulletgba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.2432080899482631
      },
      "celeste-gameplay": {
        "audio_score": 0.7353411330963947,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.7266797943477409
      },
      "chip-advance-gameplay": {
        "audio_score": 0.7167974676169271,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.952053796151196
      },
      "collie-defense-gameplay": {
        "audio_score": 0.5701947223151895,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.15145490524041738
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 1.0
      },
      "goodboy-gameplay": {
        "audio_score": 0.5950048125643564,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9919270994440912
      },
      "heartwrench-gameplay": {
        "audio_score": 0.4796950923494082,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.5119648557850117
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 9.999998989515044e-17
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 6.24970287758408e-8
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 1.544294435931383e-8
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 1.8973168109950565e-8
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 2.6634565673795143e-14
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 2.4306941588466394e-7
      },
      "piugba-gameplay": {
        "audio_score": 0.55383766152608,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.8856235546939856
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 1.4636172764406895e-14
      },
      "spout-gameplay": {
        "audio_score": 0.12085960768793604,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.24153286787854025
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 2.92869733735485e-15
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 5.244050450709553e-13
      },
      "tonc-snd1": {
        "audio_score": 0.762821315860115,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.983136319577008
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.12986367956390446,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.1349681068753254
      },
      "waimanu-gameplay": {
        "audio_score": 0.678980453869746,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.8794454745013287
      }
    },
    "provider": "OpenAI",
    "sections": {
      "audio": {
        "score": 0.5887573459703558,
        "subsystems": {
          "game_audio": 0.4377053002021905,
          "psg": 0.7398093917385211
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 0.2444444618936335,
        "subsystems": {
          "cpu": 0.4444444784976237,
          "dma": 0.5000000077214721,
          "halt_irq": 1.4636172764406895e-14,
          "memory": 9.486584104975277e-9,
          "timer": 2.6366687120415505e-13
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.6092722604039008,
        "subsystems": {
          "gameplay": 0.6092722604039008
        },
        "weight": 0.6
      }
    },
    "tokens_used": 240910000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 2,
        "commit_sha": "afd8a53a12a55c81e759a48610fe78fb427cd042",
        "kind": "auto-save",
        "overall": 0.011456543251514555,
        "overall_raw": 0.011456543251514555,
        "tokens": 1130000,
        "wall_clock_hours": 0.25
      },
      {
        "checkpoint_id": 3,
        "commit_sha": "4adf66bb15719242bf4ab6376310854b8046072a",
        "kind": "auto-save",
        "overall": 0.01190325637332874,
        "overall_raw": 0.01190325637332874,
        "tokens": 8650000,
        "wall_clock_hours": 0.5
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "95d7963bee34adf08bcfe41000989a10a5a9332a",
        "kind": "auto-save",
        "overall": 0.012415383133766104,
        "overall_raw": 0.012415383133766104,
        "tokens": 11780000,
        "wall_clock_hours": 0.75
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "c7e356793729a2af721c836fc25364513a065c81",
        "kind": "auto-save",
        "overall": 0.012344034807281804,
        "overall_raw": 0.012344034807281804,
        "tokens": 17290000,
        "wall_clock_hours": 1.0
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "1d51706fae2355419bf2d6e4daa5de90405b648f",
        "kind": "auto-save",
        "overall": 0.06830550215249759,
        "overall_raw": 0.06830550215249759,
        "tokens": 19500000,
        "wall_clock_hours": 1.25
      },
      {
        "checkpoint_id": 7,
        "commit_sha": "dea9bd33371c20f77612dfdac57ceec93f60d9de",
        "kind": "auto-save",
        "overall": 0.07957673062184635,
        "overall_raw": 0.07957673062184635,
        "tokens": 20560000,
        "wall_clock_hours": 1.5
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "035325f9a7c95aca2747fe45e97b88536c59cca4",
        "kind": "auto-save",
        "overall": 0.107706533688334,
        "overall_raw": 0.107706533688334,
        "tokens": 24190000,
        "wall_clock_hours": 1.75
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "78bfbfd7017fd586d6e8985c40a589941191c228",
        "kind": "auto-save",
        "overall": 0.1081014058293996,
        "overall_raw": 0.1081014058293996,
        "tokens": 25520000,
        "wall_clock_hours": 2.0
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "c26e20d41af4c53ec1530b377720ce428d121571",
        "kind": "auto-save",
        "overall": 0.1442960797932204,
        "overall_raw": 0.1442960797932204,
        "tokens": 28710000,
        "wall_clock_hours": 2.25
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "674878201df1fd54d84a64cf18401e5bc985113c",
        "kind": "auto-save",
        "overall": 0.20546594587361824,
        "overall_raw": 0.20546594587361824,
        "tokens": 30180000,
        "wall_clock_hours": 2.5
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "e307898253e035bee14b19e546b963f2e1b1387f",
        "kind": "auto-save",
        "overall": 0.3244030340393085,
        "overall_raw": 0.3244030340393085,
        "tokens": 31250000,
        "wall_clock_hours": 2.75
      },
      {
        "checkpoint_id": 13,
        "commit_sha": "17e6faeaa1f7fe719b8449f4a7dfa8916f47dbd3",
        "kind": "auto-save",
        "overall": 0.36319038867323133,
        "overall_raw": 0.36319038867323133,
        "tokens": 33670000,
        "wall_clock_hours": 3.0
      },
      {
        "checkpoint_id": 14,
        "commit_sha": "3dac6befc1509ebee21636f64e1d278380b435ca",
        "kind": "auto-save",
        "overall": 0.34367692101576397,
        "overall_raw": 0.34367692101576397,
        "tokens": 34570000,
        "wall_clock_hours": 3.25
      },
      {
        "checkpoint_id": 15,
        "commit_sha": "b73bff9ebef9f60c5a4548cc2eb98f2caedb592e",
        "kind": "auto-save",
        "overall": 0.39978152533049655,
        "overall_raw": 0.39978152533049655,
        "tokens": 35210000,
        "wall_clock_hours": 3.5
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "402639e70eae68b7aa23f2319f7c1d63c38911cd",
        "kind": "auto-save",
        "overall": 0.39984078182531135,
        "overall_raw": 0.39984078182531135,
        "tokens": 39350000,
        "wall_clock_hours": 3.75
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "be6bc707033f190544adde829786abe5a848ef30",
        "kind": "auto-save",
        "overall": 0.4001981284290594,
        "overall_raw": 0.4001981284290594,
        "tokens": 42620000,
        "wall_clock_hours": 4.25
      },
      {
        "checkpoint_id": 19,
        "commit_sha": "f988ae5414d2e74a93cdc4343a89c2738541a788",
        "kind": "auto-save",
        "overall": 0.40019812787163905,
        "overall_raw": 0.40019812787163905,
        "tokens": 44380000,
        "wall_clock_hours": 4.5
      },
      {
        "checkpoint_id": 20,
        "commit_sha": "b9f858bbe3b56ded5fced43de8cfd26a8f15edad",
        "kind": "auto-save",
        "overall": 0.4001981278716374,
        "overall_raw": 0.4001981278716374,
        "tokens": 46150000,
        "wall_clock_hours": 4.75
      },
      {
        "checkpoint_id": 21,
        "commit_sha": "e7fa391fcd6bea8b311852b54551f7a3985f3ec2",
        "kind": "auto-save",
        "overall": 0.40019812871930854,
        "overall_raw": 0.40019812871930854,
        "tokens": 46570000,
        "wall_clock_hours": 5.0
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "ca55ef61c2dfc4cb8c3791a8b33fb92c2e0bea6c",
        "kind": "auto-save",
        "overall": 0.3880971600991383,
        "overall_raw": 0.3880971600991383,
        "tokens": 51040000,
        "wall_clock_hours": 5.25
      },
      {
        "checkpoint_id": 23,
        "commit_sha": "67760544f53c3c65320f00136410c5e05c613249",
        "kind": "auto-save",
        "overall": 0.34408024190109004,
        "overall_raw": 0.34408024190109004,
        "tokens": 52730000,
        "wall_clock_hours": 5.5
      },
      {
        "checkpoint_id": 25,
        "commit_sha": "aa0b3db500db665a27dc1c7f1b0e06679490b7e6",
        "kind": "auto-save",
        "overall": 0.4212118635661246,
        "overall_raw": 0.4212118635661246,
        "tokens": 55360000,
        "wall_clock_hours": 5.963888888888889
      },
      {
        "checkpoint_id": 26,
        "commit_sha": "3aa0dc1baef5a6bf6d9fff4c0101a57ebb275d19",
        "kind": "auto-save",
        "overall": 0.4212118635097213,
        "overall_raw": 0.4212118635097213,
        "tokens": 56750000,
        "wall_clock_hours": 6.213888888888889
      },
      {
        "checkpoint_id": 27,
        "commit_sha": "4ab9b68fbb06d14f97f73c53bc2c1aa487cb0228",
        "kind": "auto-save",
        "overall": 0.4212118630828008,
        "overall_raw": 0.4212118630828008,
        "tokens": 57240000,
        "wall_clock_hours": 6.463888888888889
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "fed126d61e9ce216deb7c388ec385d89c217210d",
        "kind": "auto-save",
        "overall": 0.4212118633163777,
        "overall_raw": 0.4212118633163777,
        "tokens": 57880000,
        "wall_clock_hours": 6.713888888888889
      },
      {
        "checkpoint_id": 29,
        "commit_sha": "6a7f826ee94c1444d2342ca7fb3570bac6954b38",
        "kind": "auto-save",
        "overall": 0.421214615331447,
        "overall_raw": 0.421214615331447,
        "tokens": 59360000,
        "wall_clock_hours": 6.963888888888889
      },
      {
        "checkpoint_id": 30,
        "commit_sha": "29286ca8bc3983c1139e132340bf85a5b79061c3",
        "kind": "auto-save",
        "overall": 0.421214615331447,
        "overall_raw": 0.421214615331447,
        "tokens": 61410000,
        "wall_clock_hours": 7.213888888888889
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "f98df95f70239a6121f159c7f4e32ac2cc542447",
        "kind": "auto-save",
        "overall": 0.421214615331447,
        "overall_raw": 0.421214615331447,
        "tokens": 62260000,
        "wall_clock_hours": 7.463888888888889
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "c39df49f93c0ccd6e07ab6ae73a15dc2342e65d1",
        "kind": "auto-save",
        "overall": 0.421214615331447,
        "overall_raw": 0.421214615331447,
        "tokens": 63190000,
        "wall_clock_hours": 7.713888888888889
      },
      {
        "checkpoint_id": 33,
        "commit_sha": "9b98e17c8ecfdc4f92066c3306997ff7ca2ef733",
        "kind": "auto-save",
        "overall": 0.4212146167398307,
        "overall_raw": 0.4212146167398307,
        "tokens": 64599999,
        "wall_clock_hours": 7.963888888888889
      },
      {
        "checkpoint_id": 34,
        "commit_sha": "66c575d0cc79dd2ea0cb1407955b196778e73239",
        "kind": "auto-save",
        "overall": 0.4212146167398307,
        "overall_raw": 0.4212146167398307,
        "tokens": 66650000,
        "wall_clock_hours": 8.213888888888889
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "f107298c0317932043d09d560e3660809b610405",
        "kind": "auto-save",
        "overall": 0.4215948350249168,
        "overall_raw": 0.4215948350249168,
        "tokens": 68030000,
        "wall_clock_hours": 8.463888888888889
      },
      {
        "checkpoint_id": 36,
        "commit_sha": "4e001bbe522300a04bdeb9a40926b36b7ac98012",
        "kind": "auto-save",
        "overall": 0.42093934840333314,
        "overall_raw": 0.42093934840333314,
        "tokens": 69610000,
        "wall_clock_hours": 8.713888888888889
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "814e956922478d2797c83bb67b340ed70c337654",
        "kind": "auto-save",
        "overall": 0.42093934840333314,
        "overall_raw": 0.42093934840333314,
        "tokens": 72560000,
        "wall_clock_hours": 8.963888888888889
      },
      {
        "checkpoint_id": 38,
        "commit_sha": "e23cf635285a1a1fed67808f5fa576cefa3467f5",
        "kind": "auto-save",
        "overall": 0.42093934840333314,
        "overall_raw": 0.42093934840333314,
        "tokens": 73100000,
        "wall_clock_hours": 9.213888888888889
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "22ca741e6a11871bc722b8424d98d1c7ec38ce5f",
        "kind": "auto-save",
        "overall": 0.42093934840333314,
        "overall_raw": 0.42093934840333314,
        "tokens": 75370000,
        "wall_clock_hours": 9.463888888888889
      },
      {
        "checkpoint_id": 40,
        "commit_sha": "c6f2fb211dd8c0db4a9e1f4dbf75c640cecae6c0",
        "kind": "auto-save",
        "overall": 0.4122296365642991,
        "overall_raw": 0.4122296365642991,
        "tokens": 77810000,
        "wall_clock_hours": 9.713888888888889
      },
      {
        "checkpoint_id": 41,
        "commit_sha": "6b566e2677b8748137096c71582b014f03d40a0f",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 81830000,
        "wall_clock_hours": 9.963888888888889
      },
      {
        "checkpoint_id": 42,
        "commit_sha": "467dc99b7b83193cf26aa82c67cef8f131eb23d6",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 84520000,
        "wall_clock_hours": 10.213888888888889
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "fa0a44f789c8eca2377005cb934e5dd5a9da837c",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 85930000,
        "wall_clock_hours": 10.463888888888889
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "5022d70b5347a96961131a2882020a756019eabe",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 87500000,
        "wall_clock_hours": 10.713888888888889
      },
      {
        "checkpoint_id": 45,
        "commit_sha": "00de892e704fe886a7bcc4344406d0f6be942a92",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 89980000,
        "wall_clock_hours": 10.963888888888889
      },
      {
        "checkpoint_id": 46,
        "commit_sha": "563858a9302b34cde436b35cfca0c358e8999fc0",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 90820000,
        "wall_clock_hours": 11.213888888888889
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "7a139c439f982b5630e34dc474f2a332bcdbea45",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 93470000,
        "wall_clock_hours": 11.463888888888889
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "35fd874c7d79d99d4620a840ff703b89360093f1",
        "kind": "auto-save",
        "overall": 0.412181578595842,
        "overall_raw": 0.412181578595842,
        "tokens": 95340000,
        "wall_clock_hours": 11.713888888888889
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "735f2d84eaeb134af162d916b42e7f51e55f3548",
        "kind": "auto-save",
        "overall": 0.41197523170226114,
        "overall_raw": 0.41197523170226114,
        "tokens": 97290000,
        "wall_clock_hours": 11.963888888888889
      },
      {
        "checkpoint_id": 50,
        "commit_sha": "a36c9ab402fd87a2d4dbc079c73ad08693fef4b3",
        "kind": "auto-save",
        "overall": 0.407835530739298,
        "overall_raw": 0.407835530739298,
        "tokens": 98000000,
        "wall_clock_hours": 12.213888888888889
      },
      {
        "checkpoint_id": 51,
        "commit_sha": "a13d3839ab4d5b0064b796e68a483f85bc6bd85f",
        "kind": "auto-save",
        "overall": 0.407835530739298,
        "overall_raw": 0.407835530739298,
        "tokens": 98190000,
        "wall_clock_hours": 12.463888888888889
      },
      {
        "checkpoint_id": 52,
        "commit_sha": "aafe39529cb78792b0dd00e40c297eefc60e8ba8",
        "kind": "auto-save",
        "overall": 0.4147126154585113,
        "overall_raw": 0.4147126154585113,
        "tokens": 104240000,
        "wall_clock_hours": 12.713888888888889
      },
      {
        "checkpoint_id": 54,
        "commit_sha": "78baf9421987b90dc994a4c8fa3457f81cdc67b7",
        "kind": "auto-save",
        "overall": 0.4851343017562971,
        "overall_raw": 0.4851343017562971,
        "tokens": 118190000,
        "wall_clock_hours": 13.213888888888889
      },
      {
        "checkpoint_id": 73,
        "commit_sha": "892ff8d518466a06c52f937020dfc3d7400d7be9",
        "kind": "auto-save",
        "overall": 0.49497762676687695,
        "overall_raw": 0.49497762676687695,
        "tokens": 208950000,
        "wall_clock_hours": 17.96388888888889
      },
      {
        "checkpoint_id": 78,
        "commit_sha": "1ef152e4e0b4c34ee8481e61de2c1461fdd40c76",
        "kind": "auto-save",
        "overall": 0.4949776267668792,
        "overall_raw": 0.4949776267668792,
        "tokens": 212340000,
        "wall_clock_hours": 19.21388888888889
      },
      {
        "checkpoint_id": 79,
        "commit_sha": "1dbf87875bc5b14b285df770c9ce24ddf1074393",
        "kind": "auto-save",
        "overall": 0.4949776267668792,
        "overall_raw": 0.4949776267668792,
        "tokens": 214630000,
        "wall_clock_hours": 19.46388888888889
      },
      {
        "checkpoint_id": 80,
        "commit_sha": "e08309c54254cae64daa747670d2a3ca9662d52c",
        "kind": "auto-save",
        "overall": 0.4949776267668792,
        "overall_raw": 0.4949776267668792,
        "tokens": 216560000,
        "wall_clock_hours": 19.71388888888889
      },
      {
        "checkpoint_id": 81,
        "commit_sha": "ebb848cdd39c5f7c62da50aa71a499f1c4857810",
        "kind": "auto-save",
        "overall": 0.4949776267668792,
        "overall_raw": 0.4949776267668792,
        "tokens": 217770000,
        "wall_clock_hours": 19.96388888888889
      },
      {
        "checkpoint_id": 82,
        "commit_sha": "e573ab9b9894d9dac9498e729043434a1517b1ea",
        "kind": "auto-save",
        "overall": 0.4949776267668792,
        "overall_raw": 0.4949776267668792,
        "tokens": 221880000,
        "wall_clock_hours": 20.21388888888889
      },
      {
        "checkpoint_id": 83,
        "commit_sha": "e5411cb93ff9f90c368c17809073f1180ffeffab",
        "kind": "auto-save",
        "overall": 0.4949776267668792,
        "overall_raw": 0.4949776267668792,
        "tokens": 223730000,
        "wall_clock_hours": 20.46388888888889
      },
      {
        "checkpoint_id": 84,
        "commit_sha": "aaca8df07f91def4643036283028dbd88c72f518",
        "kind": "auto-save",
        "overall": 0.4949776267668792,
        "overall_raw": 0.4949776267668792,
        "tokens": 225670000,
        "wall_clock_hours": 20.71388888888889
      },
      {
        "checkpoint_id": 85,
        "commit_sha": "c46f5e6f8df72f74c36fc62e53397e08452ac66f",
        "kind": "auto-save",
        "overall": 0.4640461754094451,
        "overall_raw": 0.4640461754094451,
        "tokens": 226580000,
        "wall_clock_hours": 20.96388888888889
      },
      {
        "checkpoint_id": 86,
        "commit_sha": "7028edad9cdecbd3e20be21909bcceb16593bda2",
        "kind": "auto-save",
        "overall": 0.4665356256017757,
        "overall_raw": 0.4665356256017757,
        "tokens": 229860000,
        "wall_clock_hours": 21.21388888888889
      },
      {
        "checkpoint_id": 87,
        "commit_sha": "6bbc75fcf03b4fcbc75aecd81e5e1cdab757fabc",
        "kind": "auto-save",
        "overall": 0.4665356256017757,
        "overall_raw": 0.4665356256017757,
        "tokens": 232500000,
        "wall_clock_hours": 21.46388888888889
      },
      {
        "checkpoint_id": 88,
        "commit_sha": "85ed73ab4377710567173ca1e9991050b5a322a1",
        "kind": "auto-save",
        "overall": 0.4665356256017757,
        "overall_raw": 0.4665356256017757,
        "tokens": 234720000,
        "wall_clock_hours": 21.71388888888889
      },
      {
        "checkpoint_id": 90,
        "commit_sha": "e1d6900b31d1b7e1d098c4956961c33ad8788f26",
        "kind": "auto-save",
        "overall": 0.4665356256017757,
        "overall_raw": 0.4665356256017757,
        "tokens": 236230000,
        "wall_clock_hours": 22.21388888888889
      },
      {
        "checkpoint_id": 91,
        "commit_sha": "9fcc96e563b8f73ac9063931457cc0752ca9c6cd",
        "kind": "auto-save",
        "overall": 0.4665356256017757,
        "overall_raw": 0.4665356256017757,
        "tokens": 236700000,
        "wall_clock_hours": 22.46388888888889
      },
      {
        "checkpoint_id": 92,
        "commit_sha": "e792e61659136a2d8dd816817301be357860e69f",
        "kind": "auto-save",
        "overall": 0.4665356256017757,
        "overall_raw": 0.4665356256017757,
        "tokens": 237450000,
        "wall_clock_hours": 22.71388888888889
      },
      {
        "checkpoint_id": 93,
        "commit_sha": "2a9fe8b266246ae4bbc2457514de1cf8c7a4a35c",
        "kind": "auto-save",
        "overall": 0.46527557557106813,
        "overall_raw": 0.46527557557106813,
        "tokens": 237940000,
        "wall_clock_hours": 22.96388888888889
      },
      {
        "checkpoint_id": 94,
        "commit_sha": "905bf740411497b3a2701bd8beb79c12903e85f3",
        "kind": "auto-save",
        "overall": 0.5320771498876392,
        "overall_raw": 0.5320771498876392,
        "tokens": 238690000,
        "wall_clock_hours": 23.21388888888889
      },
      {
        "checkpoint_id": 95,
        "commit_sha": "12e72e8e7de830524ccbba38297dbb6351fe3179",
        "kind": "auto-save",
        "overall": 0.5322037176929686,
        "overall_raw": 0.5322037176929686,
        "tokens": 239510000,
        "wall_clock_hours": 23.46388888888889
      },
      {
        "checkpoint_id": 96,
        "commit_sha": "1bf8099aeb891c39548fe95a1e9a62f221e3fc4b",
        "kind": "auto-save",
        "overall": 0.5322037178151383,
        "overall_raw": 0.5322037178151383,
        "tokens": 240430000,
        "wall_clock_hours": 23.71388888888889
      },
      {
        "checkpoint_id": 97,
        "commit_sha": "291049db0001f2d37c58ccba53be6874f20733b5",
        "kind": "auto-save",
        "overall": 0.5322037178151383,
        "overall_raw": 0.5322037178151383,
        "tokens": 240910000,
        "wall_clock_hours": 23.96388888888889
      }
    ],
    "wall_clock_hours": 23.96388888888889
  },
  {
    "baseline": false,
    "candidate": "claude-sonnet",
    "candidate_sha256": "e21f11e04b2a54e6f0f35f9e307ccaf4023db4271bdf175af19511ccc17cfb85",
    "checkpoints_count": 54,
    "graded_at": "2026-05-03T08:36:01Z",
    "has_wasm": true,
    "label": "Claude Sonnet 4.6",
    "model": "claude-sonnet-4-6",
    "overall": 0.48756634832044743,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "bulletgba-gameplay": {
        "audio_score": 0.4958956073549056,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9964275334067249
      },
      "celeste-gameplay": {
        "audio_score": 0.5017687912745387,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.7141235587984146
      },
      "chip-advance-gameplay": {
        "audio_score": 0.043614519318760904,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9382851128230428
      },
      "collie-defense-gameplay": {
        "audio_score": 0.4121991875474484,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.009960239052970768
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 1.0
      },
      "goodboy-gameplay": {
        "audio_score": 0.5273645399147623,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9918465218787164
      },
      "heartwrench-gameplay": {
        "audio_score": 0.030843322557232825,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.04316010647563476
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 1.0
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 4.1293673070903634e-7
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 4.5477033903781955e-7
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 0.000017382629367735252
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 0.000017476977627496027
      },
      "piugba-gameplay": {
        "audio_score": 0.05703331057823782,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.8113160412802909
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 1.4636172764406895e-14
      },
      "spout-gameplay": {
        "audio_score": 0.09151685510235688,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.06150610601876756
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 2.7561764841325496e-15
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 5.628097565437776e-13
      },
      "tonc-snd1": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.966470454601582
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.22167617050451985,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.15167517357001925
      },
      "waimanu-gameplay": {
        "audio_score": 0.5176979663886114,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.8507479735197573
      }
    },
    "provider": "Anthropic",
    "sections": {
      "audio": {
        "score": 0.1713879819533792,
        "subsystems": {
          "game_audio": 0.32096870424737795,
          "psg": 0.021807259659380452
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 0.4840295356236069,
        "subsystems": {
          "cpu": 0.777781651067444,
          "dma": 0.5000002064683654,
          "halt_irq": 1.4636172764406895e-14,
          "memory": 0.5000002273851695,
          "timer": 2.827829665139551e-13
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.5941380746750837,
        "subsystems": {
          "gameplay": 0.5941380746750837
        },
        "weight": 0.6
      }
    },
    "tokens_used": 13090000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 2,
        "commit_sha": "dfa2d49150c87cad10902582b88d09cd13df46f9",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 280000,
        "wall_clock_hours": 0.25
      },
      {
        "checkpoint_id": 3,
        "commit_sha": "558f823ac6968a677fdc978517963984247fddde",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 401000,
        "wall_clock_hours": 0.5
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "aab6fc84e570907cb00eeefbfbad1c6d298eb5e2",
        "kind": "auto-save",
        "overall": 0.008467616648430898,
        "overall_raw": 0.008467616648430898,
        "tokens": 666000,
        "wall_clock_hours": 0.75
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "0b9123ac76e92422c5b7fc8e46c38fda4ce8b5b3",
        "kind": "auto-save",
        "overall": 0.008467616648430898,
        "overall_raw": 0.008467616648430898,
        "tokens": 812000,
        "wall_clock_hours": 1.0
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "bc3e7998b0c812260180cccc9f2a8d70ecb0bb64",
        "kind": "auto-save",
        "overall": 0.007898998599060144,
        "overall_raw": 0.007898998599060144,
        "tokens": 1030000,
        "wall_clock_hours": 1.25
      },
      {
        "checkpoint_id": 7,
        "commit_sha": "bce937599fa9f6a9c9672ad1361e60da5f9f6c99",
        "kind": "auto-save",
        "overall": 0.08496465341383307,
        "overall_raw": 0.08496465341383307,
        "tokens": 1180000,
        "wall_clock_hours": 1.5
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "97f49c68b9fba78609c8a655122edd8dd882a550",
        "kind": "auto-save",
        "overall": 0.08496465341383307,
        "overall_raw": 0.08496465341383307,
        "tokens": 1290000,
        "wall_clock_hours": 1.75
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "2955a7bac05d61b39a5522fe5121e34b3d4aa39f",
        "kind": "auto-save",
        "overall": 0.08496465341383307,
        "overall_raw": 0.08496465341383307,
        "tokens": 1420000,
        "wall_clock_hours": 2.0
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "50b8ad3ca0bff714a193d67e023b6f9cf59ff966",
        "kind": "auto-save",
        "overall": 0.08740913379906953,
        "overall_raw": 0.08740913379906953,
        "tokens": 1530000,
        "wall_clock_hours": 2.25
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "b6a80b8c4ef4970b95331d2cd57ad55198bcbe3b",
        "kind": "auto-save",
        "overall": 0.08824814199816752,
        "overall_raw": 0.08824814199816752,
        "tokens": 1840000,
        "wall_clock_hours": 2.5
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "60fde6cd58a4b754220b2c14f867dc1b2bdba378",
        "kind": "auto-save",
        "overall": 0.08827892866689206,
        "overall_raw": 0.08827892866689206,
        "tokens": 1950000,
        "wall_clock_hours": 2.75
      },
      {
        "checkpoint_id": 15,
        "commit_sha": "6b69904b789d5df34dd3acbebb8ee8f364f21311",
        "kind": "auto-save",
        "overall": 0.1384098779206175,
        "overall_raw": 0.1384098779206175,
        "tokens": 2340000,
        "wall_clock_hours": 3.5
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "6cff43a29808f36e3aed103cd6759687f2597594",
        "kind": "auto-save",
        "overall": 0.1384098779206175,
        "overall_raw": 0.1384098779206175,
        "tokens": 2430000,
        "wall_clock_hours": 3.75
      },
      {
        "checkpoint_id": 17,
        "commit_sha": "3bc58a28b3374234f50664058ecc8166fe32135d",
        "kind": "auto-save",
        "overall": 0.1384098779206175,
        "overall_raw": 0.1384098779206175,
        "tokens": 2550000,
        "wall_clock_hours": 4.0
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "ba21d960271e4b988a098dc9855ea1c44bb7147b",
        "kind": "auto-save",
        "overall": 0.1384098779206175,
        "overall_raw": 0.1384098779206175,
        "tokens": 2660000,
        "wall_clock_hours": 4.25
      },
      {
        "checkpoint_id": 19,
        "commit_sha": "18e0869658b04b10b2f0bc4e8717abfb9608df2a",
        "kind": "auto-save",
        "overall": 0.1384098779206175,
        "overall_raw": 0.1384098779206175,
        "tokens": 2770000,
        "wall_clock_hours": 4.5
      },
      {
        "checkpoint_id": 21,
        "commit_sha": "f148077b3e85d38b340bddf92b6f084628c63ff9",
        "kind": "auto-save",
        "overall": 0.13817544992189018,
        "overall_raw": 0.13817544992189018,
        "tokens": 3020000,
        "wall_clock_hours": 5.0
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "811a7b05f16e8d27a5f6afbd018e69e17f71485e",
        "kind": "auto-save",
        "overall": 0.13817544992189018,
        "overall_raw": 0.13817544992189018,
        "tokens": 3230000,
        "wall_clock_hours": 5.25
      },
      {
        "checkpoint_id": 23,
        "commit_sha": "3ce4b109eefa7be5af6fe589ebd085329ab95fb2",
        "kind": "auto-save",
        "overall": 0.1384098779206175,
        "overall_raw": 0.1384098779206175,
        "tokens": 3360000,
        "wall_clock_hours": 5.5
      },
      {
        "checkpoint_id": 25,
        "commit_sha": "f108922b675b2b6c609bbc7dc6e1403fd326eac8",
        "kind": "auto-save",
        "overall": 0.1384098779206175,
        "overall_raw": 0.1384098779206175,
        "tokens": 3550000,
        "wall_clock_hours": 5.804166666666666
      },
      {
        "checkpoint_id": 26,
        "commit_sha": "344c3ade7b2d482b159d557c3af2b67a2ae8d340",
        "kind": "auto-save",
        "overall": 0.467467794010385,
        "overall_raw": 0.467467794010385,
        "tokens": 3670000,
        "wall_clock_hours": 6.054166666666666
      },
      {
        "checkpoint_id": 27,
        "commit_sha": "f6d60b1664c282ab720853a1c8ca2edd236126a7",
        "kind": "auto-save",
        "overall": 0.4554762145934883,
        "overall_raw": 0.4554762145934883,
        "tokens": 3790000,
        "wall_clock_hours": 6.304166666666666
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "1a43c2ed47e02d903f4371458b69312dfc48b4a2",
        "kind": "auto-save",
        "overall": 0.4554762145934883,
        "overall_raw": 0.4554762145934883,
        "tokens": 3910000,
        "wall_clock_hours": 6.554166666666666
      },
      {
        "checkpoint_id": 29,
        "commit_sha": "3a21493d9e4be22824378b34df0b8c3d924ddd69",
        "kind": "auto-save",
        "overall": 0.4554762145934883,
        "overall_raw": 0.4554762145934883,
        "tokens": 4040000,
        "wall_clock_hours": 6.804166666666666
      },
      {
        "checkpoint_id": 30,
        "commit_sha": "0ff7fc81595c4458e1615b717dd4e3c27920bc8d",
        "kind": "auto-save",
        "overall": 0.4675462131250594,
        "overall_raw": 0.4675462131250594,
        "tokens": 4160000,
        "wall_clock_hours": 7.054166666666666
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "f86385107c0ffb89d43f9e624dcada6b1744ad2d",
        "kind": "auto-save",
        "overall": 0.4675462131250594,
        "overall_raw": 0.4675462131250594,
        "tokens": 4260000,
        "wall_clock_hours": 7.304166666666666
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "5afc5a0113eecc6e386ba5c8b7dcaf1f1281258e",
        "kind": "auto-save",
        "overall": 0.4675462131250594,
        "overall_raw": 0.4675462131250594,
        "tokens": 4390000,
        "wall_clock_hours": 7.554166666666666
      },
      {
        "checkpoint_id": 33,
        "commit_sha": "11943145cf036b31373938f8a7e124e4fceed73f",
        "kind": "auto-save",
        "overall": 0.46755525006909726,
        "overall_raw": 0.46755525006909726,
        "tokens": 4560000,
        "wall_clock_hours": 7.804166666666666
      },
      {
        "checkpoint_id": 34,
        "commit_sha": "4fa7a2d19fe68a657e26adfae555b632f0092e86",
        "kind": "auto-save",
        "overall": 0.46755525006909726,
        "overall_raw": 0.46755525006909726,
        "tokens": 4670000,
        "wall_clock_hours": 8.054166666666667
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "8555a1b5964903c17905d218db0161f8675d2acb",
        "kind": "auto-save",
        "overall": 0.46755525006909726,
        "overall_raw": 0.46755525006909726,
        "tokens": 5570000,
        "wall_clock_hours": 8.304166666666667
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "1a7b3367bdb687be50c78f947a9f3369a1346598",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 6620000,
        "wall_clock_hours": 8.804166666666667
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "a9a96444e03195c8fb6129d94e26d89fa3a8cddd",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 7050000,
        "wall_clock_hours": 9.304166666666667
      },
      {
        "checkpoint_id": 41,
        "commit_sha": "1a9bcf9619eefe2ededfb6f9801c71527d5d3153",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 7420000,
        "wall_clock_hours": 9.804166666666667
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "21e9c6ca7ad339c438a00509210bbaefba75ceed",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 7650000,
        "wall_clock_hours": 10.304166666666667
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "0e8503f26f4c4a09832fc9fbe5ee7617906d39e7",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 7870000,
        "wall_clock_hours": 10.554166666666667
      },
      {
        "checkpoint_id": 45,
        "commit_sha": "818725b94e787785d3bc80ffe0e0859ab76bf7dc",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 8660000,
        "wall_clock_hours": 10.804166666666667
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "bff4c21dcf411c5a494c83ff79adec28019305fb",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 8930000,
        "wall_clock_hours": 11.304166666666667
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "83414a0ee10792c295aba20c10e800888d826e21",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 9040000,
        "wall_clock_hours": 11.554166666666667
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "9ada89c145211d6fd4fac7e949e237f0afc938ec",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 9320000,
        "wall_clock_hours": 11.804166666666667
      },
      {
        "checkpoint_id": 50,
        "commit_sha": "6bfec898f6ffaa7019ff0962f6829a779a7e70c9",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 9980000,
        "wall_clock_hours": 12.054166666666667
      },
      {
        "checkpoint_id": 51,
        "commit_sha": "6e3c1614e344eb864ca28fca805cf1a1c6403b0e",
        "kind": "auto-save",
        "overall": 0.4675933349982524,
        "overall_raw": 0.4675933349982524,
        "tokens": 10380000,
        "wall_clock_hours": 12.304166666666667
      },
      {
        "checkpoint_id": 53,
        "commit_sha": "aa69125489a35f7ca545448a07a9bf379a26f6c8",
        "kind": "auto-save",
        "overall": 0.46755525006909726,
        "overall_raw": 0.46755525006909726,
        "tokens": 10710000,
        "wall_clock_hours": 12.804166666666667
      },
      {
        "checkpoint_id": 54,
        "commit_sha": "e6a38971ad7a5ab12d11c9ddc171b341be5fe8a8",
        "kind": "auto-save",
        "overall": 0.45672411943184743,
        "overall_raw": 0.45672411943184743,
        "tokens": 10820000,
        "wall_clock_hours": 13.054166666666667
      },
      {
        "checkpoint_id": 56,
        "commit_sha": "081ed28536d1f7ba507ce62fa9b2da919832f433",
        "kind": "auto-save",
        "overall": 0.4677441962117727,
        "overall_raw": 0.4677441962117727,
        "tokens": 11030000,
        "wall_clock_hours": 13.554166666666667
      },
      {
        "checkpoint_id": 57,
        "commit_sha": "1bd73d010cbf5d94b8747357d863775de46fc30a",
        "kind": "auto-save",
        "overall": 0.4677441962117727,
        "overall_raw": 0.4677441962117727,
        "tokens": 11100000,
        "wall_clock_hours": 13.804166666666667
      },
      {
        "checkpoint_id": 59,
        "commit_sha": "ffc3959d50c67120cb1fb702fac7c40084bbf41b",
        "kind": "auto-save",
        "overall": 0.4677441962117727,
        "overall_raw": 0.4677441962117727,
        "tokens": 11260000,
        "wall_clock_hours": 14.304166666666667
      },
      {
        "checkpoint_id": 60,
        "commit_sha": "be0754f4a862844d3615924868ee7036f2a8afce",
        "kind": "auto-save",
        "overall": 0.4677441962117727,
        "overall_raw": 0.4677441962117727,
        "tokens": 11330000,
        "wall_clock_hours": 14.554166666666667
      },
      {
        "checkpoint_id": 61,
        "commit_sha": "ec7d866195edca22e300d02b61d3e589d11c3e59",
        "kind": "auto-save",
        "overall": 0.4677441962117727,
        "overall_raw": 0.4677441962117727,
        "tokens": 11660000,
        "wall_clock_hours": 14.804166666666667
      },
      {
        "checkpoint_id": 63,
        "commit_sha": "ffa3d6b4c79d4b310e8b442ce2f3eb8203d63264",
        "kind": "auto-save",
        "overall": 0.4677348478676867,
        "overall_raw": 0.4677348478676867,
        "tokens": 11840000,
        "wall_clock_hours": 15.304166666666667
      },
      {
        "checkpoint_id": 64,
        "commit_sha": "dbdd55256754ae68d1924573ea29ff6e4163452c",
        "kind": "auto-save",
        "overall": 0.4677348478676867,
        "overall_raw": 0.4677348478676867,
        "tokens": 12080000,
        "wall_clock_hours": 15.554166666666667
      },
      {
        "checkpoint_id": 66,
        "commit_sha": "1222193479f943115d5cea8f87871acf4a5dd4e6",
        "kind": "auto-save",
        "overall": 0.4675422842671018,
        "overall_raw": 0.4675422842671018,
        "tokens": 12480000,
        "wall_clock_hours": 16.054166666666667
      },
      {
        "checkpoint_id": 68,
        "commit_sha": "ddcfebb7da44e37d3f8407a4581acdbb7993133a",
        "kind": "auto-save",
        "overall": 0.4677404548544844,
        "overall_raw": 0.4677404548544844,
        "tokens": 12710000,
        "wall_clock_hours": 16.554166666666667
      },
      {
        "checkpoint_id": 69,
        "commit_sha": "98a3a3ce6e9ea89d2b18299b6cf4cfc9263408d3",
        "kind": "auto-save",
        "overall": 0.48397160514136006,
        "overall_raw": 0.48397160514136006,
        "tokens": 12990000,
        "wall_clock_hours": 16.804166666666667
      },
      {
        "checkpoint_id": 70,
        "commit_sha": "d2d1abdf4119d5bf58f3a2953eeb9456ed2ead07",
        "kind": "auto-save",
        "overall": 0.48756634832044743,
        "overall_raw": 0.48756634832044743,
        "tokens": 13090000,
        "wall_clock_hours": 17.054166666666667
      }
    ],
    "wall_clock_hours": 17.054166666666667
  },
  {
    "baseline": false,
    "candidate": "claude-opus-4-6",
    "candidate_sha256": "51b909de5ed5af04cd7018f844b344a157ea45c893fe66d8896e7b9c8be3fe48",
    "checkpoints_count": 75,
    "graded_at": "2026-05-02T00:36:19Z",
    "has_wasm": true,
    "label": "Claude Opus 4.6",
    "model": "claude-opus-4-6",
    "overall": 0.4411559216788414,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.929491501082092e-13
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "bulletgba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9971310329420556
      },
      "celeste-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.19106454069020157
      },
      "chip-advance-gameplay": {
        "audio_score": 0.006899780438069056,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9520476433207584
      },
      "collie-defense-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.00902454960310718
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 1.0
      },
      "goodboy-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.967828791719496
      },
      "heartwrench-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.2635382418526011
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 1.0
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 5.70412244933296e-16
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 3.930911453089311e-7
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 0.000017382629367735252
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 0.000017476977627496027
      },
      "piugba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9545590500058508
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 1.4636172764406895e-14
      },
      "spout-gameplay": {
        "audio_score": 0.06631014602539007,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.06204221114660229
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 2.7561764841325496e-15
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 5.628097565437776e-13
      },
      "tonc-snd1": {
        "audio_score": 0.051098260336569334,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.932743660581806
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.17564449208454608
      },
      "waimanu-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9325353531496104
      }
    },
    "provider": "Anthropic",
    "sections": {
      "audio": {
        "score": 0.014499510193659595,
        "subsystems": {
          "game_audio": 0.0,
          "psg": 0.02899902038731919
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 0.43541839808328303,
        "subsystems": {
          "cpu": 0.6666705399564431,
          "dma": 0.5000000000000003,
          "halt_irq": 1.4636172764406895e-14,
          "memory": 0.5000001965455727,
          "timer": 2.827829665139551e-13
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.5852872333724214,
        "subsystems": {
          "gameplay": 0.5852872333724214
        },
        "weight": 0.6
      }
    },
    "tokens_used": 11270000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 1,
        "commit_sha": "1654f4fc146932576e88a1d5410f17b93210a0f8",
        "kind": "auto-save",
        "overall": 0.008484301580782602,
        "overall_raw": 0.008484301580782602,
        "tokens": 196000,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 2,
        "commit_sha": "7149463d09cf7637800b0c17c2fc4b159b4e4b4f",
        "kind": "auto-save",
        "overall": 0.01358434767410466,
        "overall_raw": 0.01358434767410466,
        "tokens": 309000,
        "wall_clock_hours": 0.25
      },
      {
        "checkpoint_id": 3,
        "commit_sha": "f459c0d37ce4847861193d57c8d79dacee3fc74f",
        "kind": "auto-save",
        "overall": 0.01358434767410466,
        "overall_raw": 0.01358434767410466,
        "tokens": 422000,
        "wall_clock_hours": 0.5
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "1d4059ecb4202bc78a700d2648f4effb63ebf290",
        "kind": "auto-save",
        "overall": 0.4691916081946573,
        "overall_raw": 0.4691916081946573,
        "tokens": 559000,
        "wall_clock_hours": 0.75
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "cef608fd25ef959d0b67e1575c1a8b1bbf898ad4",
        "kind": "auto-save",
        "overall": 0.4692246883995499,
        "overall_raw": 0.4692246883995499,
        "tokens": 795000,
        "wall_clock_hours": 1.0
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "dcf60406c1d1432f0e20db59eb13d846d4da6fb1",
        "kind": "auto-save",
        "overall": 0.4692246883995499,
        "overall_raw": 0.4692246883995499,
        "tokens": 894000,
        "wall_clock_hours": 1.25
      },
      {
        "checkpoint_id": 7,
        "commit_sha": "8e8f2cca78792008f312bb33718bc702f134b4ac",
        "kind": "auto-save",
        "overall": 0.4685634960702696,
        "overall_raw": 0.4685634960702696,
        "tokens": 990000,
        "wall_clock_hours": 1.5
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "4a35934a2ff88d2987855f6701e6ef2135010407",
        "kind": "auto-save",
        "overall": 0.433730186015707,
        "overall_raw": 0.433730186015707,
        "tokens": 1090000,
        "wall_clock_hours": 1.75
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "24649afd6bdee5a67c9d23084a6081d76e1588ae",
        "kind": "auto-save",
        "overall": 0.4263147844910356,
        "overall_raw": 0.4263147844910356,
        "tokens": 1270000,
        "wall_clock_hours": 2.0
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "2188594aee34980eda6a12503a444d42da9f3017",
        "kind": "auto-save",
        "overall": 0.4244259496988931,
        "overall_raw": 0.4244259496988931,
        "tokens": 1370000,
        "wall_clock_hours": 2.25
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "e71ce0899c3925ce49f5d3ec689f2d7249559b43",
        "kind": "auto-save",
        "overall": 0.42887909632881455,
        "overall_raw": 0.42887909632881455,
        "tokens": 1480000,
        "wall_clock_hours": 2.5
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "91e78c15401b4172abc4a9a861c3d1292616a15e",
        "kind": "auto-save",
        "overall": 0.4246536305655368,
        "overall_raw": 0.4246536305655368,
        "tokens": 1580000,
        "wall_clock_hours": 2.75
      },
      {
        "checkpoint_id": 13,
        "commit_sha": "3da467fd6133607afdc7f3c1f2e1ae232b3ce7e5",
        "kind": "auto-save",
        "overall": 0.4246536305655368,
        "overall_raw": 0.4246536305655368,
        "tokens": 1750000,
        "wall_clock_hours": 3.0
      },
      {
        "checkpoint_id": 14,
        "commit_sha": "e01128bf34e4942cf2773e5c2e7fdef9fcc79811",
        "kind": "auto-save",
        "overall": 0.4347636003763266,
        "overall_raw": 0.4347636003763266,
        "tokens": 1840000,
        "wall_clock_hours": 3.25
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "f9b3c6a93fe6cb392a4e0e18c6ce5565856dc87a",
        "kind": "auto-save",
        "overall": 0.4246536305655368,
        "overall_raw": 0.4246536305655368,
        "tokens": 2000000,
        "wall_clock_hours": 3.75
      },
      {
        "checkpoint_id": 17,
        "commit_sha": "8e24614b74ad647f8e818909e113fbb808355b0c",
        "kind": "auto-save",
        "overall": 0.41785921028611434,
        "overall_raw": 0.41785921028611434,
        "tokens": 2180000,
        "wall_clock_hours": 4.0
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "0518c2b089f91a55102e584c35fe290f2a303973",
        "kind": "auto-save",
        "overall": 0.4200093638894577,
        "overall_raw": 0.4200093638894577,
        "tokens": 2340000,
        "wall_clock_hours": 4.25
      },
      {
        "checkpoint_id": 19,
        "commit_sha": "f33dd1d26227b0f142f4ded7b2de5ace20bfc6b5",
        "kind": "auto-save",
        "overall": 0.4185957729033762,
        "overall_raw": 0.4185957729033762,
        "tokens": 2440000,
        "wall_clock_hours": 4.5
      },
      {
        "checkpoint_id": 21,
        "commit_sha": "15b2e9695cbc47e60fdd11f4969e9e0cdcc0458b",
        "kind": "auto-save",
        "overall": 0.4200196378643035,
        "overall_raw": 0.4200196378643035,
        "tokens": 2590000,
        "wall_clock_hours": 5.0
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "c34cda62dbe131f320eaa7ba29cbe357362a9397",
        "kind": "auto-save",
        "overall": 0.4200196378643035,
        "overall_raw": 0.4200196378643035,
        "tokens": 2680000,
        "wall_clock_hours": 5.25
      },
      {
        "checkpoint_id": 23,
        "commit_sha": "eab797201170e68a08752941766892c931ba30a8",
        "kind": "auto-save",
        "overall": 0.4200196378643035,
        "overall_raw": 0.4200196378643035,
        "tokens": 2830000,
        "wall_clock_hours": 5.5
      },
      {
        "checkpoint_id": 24,
        "commit_sha": "22bba5fa4bf2b303a53f175001bcb7f56b12588c",
        "kind": "auto-save",
        "overall": 0.4200196378643035,
        "overall_raw": 0.4200196378643035,
        "tokens": 2960000,
        "wall_clock_hours": 5.75
      },
      {
        "checkpoint_id": 25,
        "commit_sha": "31b6fa95fcdd490e4bdffbc64c2628271ebc7d81",
        "kind": "auto-save",
        "overall": 0.4309015707627567,
        "overall_raw": 0.4309015707627567,
        "tokens": 3070000,
        "wall_clock_hours": 6.0
      },
      {
        "checkpoint_id": 27,
        "commit_sha": "b46f459cfc3a883d7dd53116749fb9017b032a04",
        "kind": "auto-save",
        "overall": 0.4200196378643035,
        "overall_raw": 0.4200196378643035,
        "tokens": 3230000,
        "wall_clock_hours": 6.5
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "a77c07881bd3f224411f6999df09de408f1439c8",
        "kind": "auto-save",
        "overall": 0.4194792954515567,
        "overall_raw": 0.4194792954515567,
        "tokens": 3340000,
        "wall_clock_hours": 6.75
      },
      {
        "checkpoint_id": 29,
        "commit_sha": "107422fd2a8a99ea6d8da3cfcb783ad3d31903c3",
        "kind": "auto-save",
        "overall": 0.4200196378643035,
        "overall_raw": 0.4200196378643035,
        "tokens": 3440000,
        "wall_clock_hours": 7.0
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "990270d7d76e32a0977a8060d18e815bf81ea616",
        "kind": "auto-save",
        "overall": 0.4199797194427875,
        "overall_raw": 0.4199797194427875,
        "tokens": 3610000,
        "wall_clock_hours": 7.5
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "1052729572d495ae5cf030c9149f4ae0c267ffad",
        "kind": "auto-save",
        "overall": 0.4198123153492111,
        "overall_raw": 0.4198123153492111,
        "tokens": 3690000,
        "wall_clock_hours": 7.75
      },
      {
        "checkpoint_id": 34,
        "commit_sha": "66b9be88fcb1ade891e0fb736bcfc3125731ea12",
        "kind": "auto-save",
        "overall": 0.4197896884478733,
        "overall_raw": 0.4197896884478733,
        "tokens": 3870000,
        "wall_clock_hours": 8.25
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "aeaa7c7b727c5d121aeaec830b59721dd3e4b03a",
        "kind": "auto-save",
        "overall": 0.419920632516072,
        "overall_raw": 0.419920632516072,
        "tokens": 3940000,
        "wall_clock_hours": 8.5
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "1b7d7de0d14ac4757bccbf32517c818d679dbfc5",
        "kind": "auto-save",
        "overall": 0.4197896884478733,
        "overall_raw": 0.4197896884478733,
        "tokens": 4130000,
        "wall_clock_hours": 9.0
      },
      {
        "checkpoint_id": 38,
        "commit_sha": "509807856d851f8fd59970ffd30aeeb8cda4a017",
        "kind": "auto-save",
        "overall": 0.419920632516072,
        "overall_raw": 0.419920632516072,
        "tokens": 4179999,
        "wall_clock_hours": 9.25
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "30a28092ccbde95bfb113efbf693bfc192eac46f",
        "kind": "auto-save",
        "overall": 0.4197896884478733,
        "overall_raw": 0.4197896884478733,
        "tokens": 4300000,
        "wall_clock_hours": 9.5
      },
      {
        "checkpoint_id": 41,
        "commit_sha": "3322ea39c42dba2ee4a8ee6a22c16e8e03941b45",
        "kind": "auto-save",
        "overall": 0.4335752677244952,
        "overall_raw": 0.4335752677244952,
        "tokens": 4520000,
        "wall_clock_hours": 10.0
      },
      {
        "checkpoint_id": 42,
        "commit_sha": "ac203d6f878320399d9612b161d2469953fe9593",
        "kind": "auto-save",
        "overall": 0.4197896884478808,
        "overall_raw": 0.4197896884478808,
        "tokens": 4610000,
        "wall_clock_hours": 10.25
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "2faac5d1e210dd232fc1f099332186e11dbe0d4f",
        "kind": "auto-save",
        "overall": 0.41709908533321577,
        "overall_raw": 0.41709908533321577,
        "tokens": 4690000,
        "wall_clock_hours": 10.5
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "47ffaadd847c131200dc06875230ec4551fbaab6",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 4770000,
        "wall_clock_hours": 10.75
      },
      {
        "checkpoint_id": 45,
        "commit_sha": "ba3752e0d7a0937bd434b9253b6d026369a9b5c6",
        "kind": "auto-save",
        "overall": 0.428146536761662,
        "overall_raw": 0.428146536761662,
        "tokens": 4980000,
        "wall_clock_hours": 11.0
      },
      {
        "checkpoint_id": 46,
        "commit_sha": "47e8f3389c0a1bac338d717371c421dcb172ab02",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 5060000,
        "wall_clock_hours": 11.25
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "1d775709d01223bf6dd5b5e6c9b0b72b83cb5c32",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 5160000,
        "wall_clock_hours": 11.5
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "5e572ae858f557477c74d65c2423a376fedfdc2b",
        "kind": "auto-save",
        "overall": 0.4226144568165076,
        "overall_raw": 0.4226144568165076,
        "tokens": 5260000,
        "wall_clock_hours": 11.75
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "0a8ce09537a35c5066df2bd61843a41e654d7d5c",
        "kind": "auto-save",
        "overall": 0.43533372623077093,
        "overall_raw": 0.43533372623077093,
        "tokens": 5430000,
        "wall_clock_hours": 12.0
      },
      {
        "checkpoint_id": 50,
        "commit_sha": "4765d3f9d7a51374c12eeec6c82b3491cca33034",
        "kind": "auto-save",
        "overall": 0.4199766721644114,
        "overall_raw": 0.4199766721644114,
        "tokens": 5540000,
        "wall_clock_hours": 12.25
      },
      {
        "checkpoint_id": 51,
        "commit_sha": "5cdfa0d324efa83a4a1f54107a232599c8de5ab0",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 5630000,
        "wall_clock_hours": 12.5
      },
      {
        "checkpoint_id": 52,
        "commit_sha": "a5d15dfc998cb2dad9a3acfc4325c5fea3f29113",
        "kind": "auto-save",
        "overall": 0.44864668508058875,
        "overall_raw": 0.44864668508058875,
        "tokens": 5690000,
        "wall_clock_hours": 12.75
      },
      {
        "checkpoint_id": 53,
        "commit_sha": "3843350ccd1f8e6f03e69cfe729c0792d64119df",
        "kind": "auto-save",
        "overall": 0.45436088706374056,
        "overall_raw": 0.45436088706374056,
        "tokens": 5740000,
        "wall_clock_hours": 13.0
      },
      {
        "checkpoint_id": 54,
        "commit_sha": "27334bf0c80f1535e88b0787e273424df76de729",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 6030000,
        "wall_clock_hours": 13.25
      },
      {
        "checkpoint_id": 55,
        "commit_sha": "2f1d9d7d560f37d8c891c2b258711aa53d6ec4c7",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 6190000,
        "wall_clock_hours": 13.5
      },
      {
        "checkpoint_id": 56,
        "commit_sha": "9173b49227ed1dc1f31258ce8390d676b48eb225",
        "kind": "auto-save",
        "overall": 0.43530398163041056,
        "overall_raw": 0.43530398163041056,
        "tokens": 6330000,
        "wall_clock_hours": 13.75
      },
      {
        "checkpoint_id": 57,
        "commit_sha": "0067efff94a1cc76edda2d5797c407e33e6a26f2",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 6420000,
        "wall_clock_hours": 14.0
      },
      {
        "checkpoint_id": 58,
        "commit_sha": "2db379573355b07eee93f88a1e2d8b394e002765",
        "kind": "auto-save",
        "overall": 0.4213594025028032,
        "overall_raw": 0.4213594025028032,
        "tokens": 6610000,
        "wall_clock_hours": 14.25
      },
      {
        "checkpoint_id": 60,
        "commit_sha": "2f75e563e254fe26e0e56d99ab92a8979f5f6d71",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 6860000,
        "wall_clock_hours": 14.75
      },
      {
        "checkpoint_id": 62,
        "commit_sha": "03565ba2eaf4be750f548276f3a79cd90e3344e2",
        "kind": "auto-save",
        "overall": 0.4198386686086161,
        "overall_raw": 0.4198386686086161,
        "tokens": 6990000,
        "wall_clock_hours": 15.25
      },
      {
        "checkpoint_id": 63,
        "commit_sha": "f73e6d98fc805a055222ec64d5f3bab2cc07322e",
        "kind": "auto-save",
        "overall": 0.4198386686086161,
        "overall_raw": 0.4198386686086161,
        "tokens": 7330000,
        "wall_clock_hours": 15.5
      },
      {
        "checkpoint_id": 64,
        "commit_sha": "7582b180a6f5122b1dc6990e4c085b9c3f6f0cc6",
        "kind": "auto-save",
        "overall": 0.4170757442192285,
        "overall_raw": 0.4170757442192285,
        "tokens": 7460000,
        "wall_clock_hours": 15.75
      },
      {
        "checkpoint_id": 65,
        "commit_sha": "c6782795c891cbaa5465d44d1b75776e9e49fbf7",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 7560000,
        "wall_clock_hours": 16.0
      },
      {
        "checkpoint_id": 66,
        "commit_sha": "e2a67338098daf2f6e14df8d47a9ccef41a12cd6",
        "kind": "auto-save",
        "overall": 0.4313014839670069,
        "overall_raw": 0.4313014839670069,
        "tokens": 7710000,
        "wall_clock_hours": 16.25
      },
      {
        "checkpoint_id": 67,
        "commit_sha": "f28b3e591cad91ce4db8fa8477406ae5a9241b61",
        "kind": "auto-save",
        "overall": 0.4313014839670069,
        "overall_raw": 0.4313014839670069,
        "tokens": 7850000,
        "wall_clock_hours": 16.5
      },
      {
        "checkpoint_id": 68,
        "commit_sha": "c13b64cd23c252d9932122b6c1071bbda3d609c0",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 8029999,
        "wall_clock_hours": 16.75
      },
      {
        "checkpoint_id": 69,
        "commit_sha": "b747caa76e6a3b8d55e16021bc0580affa470d00",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 8189999,
        "wall_clock_hours": 17.0
      },
      {
        "checkpoint_id": 70,
        "commit_sha": "e64c26673f882f53ac334cbe7f884784674e234a",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 8450000,
        "wall_clock_hours": 17.25
      },
      {
        "checkpoint_id": 71,
        "commit_sha": "c89417a09a07f855256d366697875aaefb52ef21",
        "kind": "auto-save",
        "overall": 0.41980198860438694,
        "overall_raw": 0.41980198860438694,
        "tokens": 8730000,
        "wall_clock_hours": 17.5
      },
      {
        "checkpoint_id": 72,
        "commit_sha": "3ef035e951be968e6b9015c3d085bf6a01bf5623",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 8780000,
        "wall_clock_hours": 17.75
      },
      {
        "checkpoint_id": 73,
        "commit_sha": "a2c2000b9109ec9dc564bdecba0eefb2510e242d",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 8950000,
        "wall_clock_hours": 18.0
      },
      {
        "checkpoint_id": 74,
        "commit_sha": "f0151b494acb0f54775eec404227ae9001126ea4",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 9010000,
        "wall_clock_hours": 18.25
      },
      {
        "checkpoint_id": 75,
        "commit_sha": "251deab9eedc9f4f94593d7cb6ed46d089885125",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 9340000,
        "wall_clock_hours": 18.5
      },
      {
        "checkpoint_id": 76,
        "commit_sha": "f0def970f1e69027d14595ccdfce517f13876ef9",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 9410000,
        "wall_clock_hours": 18.75
      },
      {
        "checkpoint_id": 77,
        "commit_sha": "3285eb2e6890e6db17dcbb66ea4705bd0c3851a8",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 9480000,
        "wall_clock_hours": 19.0
      },
      {
        "checkpoint_id": 79,
        "commit_sha": "1216b2810735bac268068d363a5ca89fd5c70842",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 9830000,
        "wall_clock_hours": 19.5
      },
      {
        "checkpoint_id": 80,
        "commit_sha": "aaddfa291a295f8dbee2f6ca3b764439759e469f",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 10260000,
        "wall_clock_hours": 19.75
      },
      {
        "checkpoint_id": 81,
        "commit_sha": "fc61c965222f5b1870fea5c3a4f51760610a4605",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 10630000,
        "wall_clock_hours": 20.0
      },
      {
        "checkpoint_id": 82,
        "commit_sha": "78262f17383826e866dc4ecdbc0aca095e078485",
        "kind": "auto-save",
        "overall": 0.428146536761662,
        "overall_raw": 0.428146536761662,
        "tokens": 10720000,
        "wall_clock_hours": 20.25
      },
      {
        "checkpoint_id": 83,
        "commit_sha": "2d0784f0a3f0115900bf35b0fac53b0549934412",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 10850000,
        "wall_clock_hours": 20.5
      },
      {
        "checkpoint_id": 85,
        "commit_sha": "aab520e3831896712da0aa965235e452af23b7af",
        "kind": "auto-save",
        "overall": 0.4198019886043945,
        "overall_raw": 0.4198019886043945,
        "tokens": 11160000,
        "wall_clock_hours": 21.0
      },
      {
        "checkpoint_id": 86,
        "commit_sha": "c6954e5cac128612c99ddb04348e6e2b7d7786c7",
        "kind": "auto-save",
        "overall": 0.4411559216788414,
        "overall_raw": 0.4411559216788414,
        "tokens": 11270000,
        "wall_clock_hours": 21.25
      }
    ],
    "wall_clock_hours": 21.25
  },
  {
    "baseline": false,
    "candidate": "claude-opus",
    "candidate_sha256": "020d8cc97aafbfa2ba4a53b9df028a37e5279080172986a406f762e2b4536266",
    "checkpoints_count": 68,
    "graded_at": "2026-05-02T00:36:17Z",
    "has_wasm": true,
    "label": "Claude Opus 4.7",
    "model": "claude-opus-4-7",
    "overall": 0.43811361876085897,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "bulletgba-gameplay": {
        "audio_score": 0.9737818454743596,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.4857673180600019
      },
      "celeste-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.2035166136670168
      },
      "chip-advance-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.028613544664125024
      },
      "collie-defense-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.8927808940392484
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 1.0
      },
      "goodboy-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.7717899713113544
      },
      "heartwrench-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.8374233361055836
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 1.0
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 2.258255007713836e-6
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 5.787076546514097e-7
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 0.000017382629367735252
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "piugba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.15046982545438034
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 1.4636172764406895e-14
      },
      "spout-gameplay": {
        "audio_score": 0.18343032652297311,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.27596032993695396
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 2.7561764841325496e-15
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 5.628097565437776e-13
      },
      "tonc-snd1": {
        "audio_score": 0.11878683466212886,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.983136319577008
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.22151150275145587
      },
      "waimanu-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.8641743503925279
      }
    },
    "provider": "Anthropic",
    "sections": {
      "audio": {
        "score": 0.09925255477084362,
        "subsystems": {
          "game_audio": 0.1391116922106228,
          "psg": 0.05939341733106443
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 0.5326399010444537,
        "subsystems": {
          "cpu": 0.8888908202921519,
          "dma": 0.5000011291275038,
          "halt_irq": 1.4636172764406895e-14,
          "memory": 0.5000002893538273,
          "timer": 2.827829665139551e-13
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.5195585459963324,
        "subsystems": {
          "gameplay": 0.5195585459963324
        },
        "weight": 0.6
      }
    },
    "tokens_used": 80090000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 2,
        "commit_sha": "5d496cf0ff345c268a618e69c10fef08ec44e8e0",
        "kind": "auto-save",
        "overall": 0.005191485006684486,
        "overall_raw": 0.005191485006684486,
        "tokens": 202000,
        "wall_clock_hours": 0.25
      },
      {
        "checkpoint_id": 3,
        "commit_sha": "0421785f3210831ce55ccdb2baf5ba6b013d5f9b",
        "kind": "auto-save",
        "overall": 0.24391187409090223,
        "overall_raw": 0.24391187409090223,
        "tokens": 347000,
        "wall_clock_hours": 0.5
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "12aa23b02ca0127df600b8dce826ff37a1b03ecd",
        "kind": "auto-save",
        "overall": 0.22696183571900053,
        "overall_raw": 0.22696183571900053,
        "tokens": 453000,
        "wall_clock_hours": 0.75
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "7afc75186b1af0aed8b7c70fd9761a8ecb824c22",
        "kind": "auto-save",
        "overall": 0.22696183571900053,
        "overall_raw": 0.22696183571900053,
        "tokens": 563000,
        "wall_clock_hours": 1.0
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "d5df1fee243635ec6675612ec603f13c393f7b10",
        "kind": "auto-save",
        "overall": 0.2326529315280994,
        "overall_raw": 0.2326529315280994,
        "tokens": 678000,
        "wall_clock_hours": 1.25
      },
      {
        "checkpoint_id": 7,
        "commit_sha": "4c1555028bfd61111149bc41a0f4adca9125e06a",
        "kind": "auto-save",
        "overall": 0.26390438134418903,
        "overall_raw": 0.26390438134418903,
        "tokens": 756000,
        "wall_clock_hours": 1.5
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "2c1481ec26bcf1343cf215a07a42d7609b911ad6",
        "kind": "auto-save",
        "overall": 0.23116752111229943,
        "overall_raw": 0.23116752111229943,
        "tokens": 859000,
        "wall_clock_hours": 1.75
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "537a15410560ea0f455711020c0c29cdb00ab6ea",
        "kind": "auto-save",
        "overall": 0.22800419504583183,
        "overall_raw": 0.22800419504583183,
        "tokens": 935000,
        "wall_clock_hours": 2.0
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "227b952bc133c70687493dfcde641ed817658ade",
        "kind": "auto-save",
        "overall": 0.2272419627789211,
        "overall_raw": 0.2272419627789211,
        "tokens": 1020000,
        "wall_clock_hours": 2.25
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "5ca340b422b83d45d6738f9c5ee346bd7ba27ae4",
        "kind": "auto-save",
        "overall": 0.2272419627789211,
        "overall_raw": 0.2272419627789211,
        "tokens": 1750000,
        "wall_clock_hours": 2.5
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "7cfbe48613e1099e4720a9fe2096a4d18d3d51b1",
        "kind": "auto-save",
        "overall": 0.2311740602285311,
        "overall_raw": 0.2311740602285311,
        "tokens": 2530000,
        "wall_clock_hours": 2.75
      },
      {
        "checkpoint_id": 13,
        "commit_sha": "e9c1d64af9743e99b2587d5f2306b252e8d30ebe",
        "kind": "auto-save",
        "overall": 0.2311740602285311,
        "overall_raw": 0.2311740602285311,
        "tokens": 2590000,
        "wall_clock_hours": 3.0
      },
      {
        "checkpoint_id": 14,
        "commit_sha": "b3201b8e3ead1d2d37da24c035f5d1b3aca83522",
        "kind": "auto-save",
        "overall": 0.2616872542419738,
        "overall_raw": 0.2616872542419738,
        "tokens": 3410000,
        "wall_clock_hours": 3.25
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "bddf0c12a719bd7fc552d754e2a2f94b27a50f5f",
        "kind": "auto-save",
        "overall": 0.23081842891555995,
        "overall_raw": 0.23081842891555995,
        "tokens": 5990000,
        "wall_clock_hours": 3.75
      },
      {
        "checkpoint_id": 17,
        "commit_sha": "50315c60adcba421a9b9caffb9e5657ada0f9736",
        "kind": "auto-save",
        "overall": 0.23081842891555995,
        "overall_raw": 0.23081842891555995,
        "tokens": 8760000,
        "wall_clock_hours": 4.0
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "829d9486b38d7535c7044604fcb29c5113988d0e",
        "kind": "auto-save",
        "overall": 0.23081842891555995,
        "overall_raw": 0.23081842891555995,
        "tokens": 11680000,
        "wall_clock_hours": 4.25
      },
      {
        "checkpoint_id": 19,
        "commit_sha": "96fd109689ef740f48a413bd7963f041dc6a8152",
        "kind": "auto-save",
        "overall": 0.23081842891555995,
        "overall_raw": 0.23081842891555995,
        "tokens": 11820000,
        "wall_clock_hours": 4.5
      },
      {
        "checkpoint_id": 20,
        "commit_sha": "f9db69154697410ade750b14f7e35cf1fad9e4eb",
        "kind": "auto-save",
        "overall": 0.23081842891555995,
        "overall_raw": 0.23081842891555995,
        "tokens": 11920000,
        "wall_clock_hours": 4.75
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "d71579e13453ef2d120715b5927d0c645bfdd8e3",
        "kind": "auto-save",
        "overall": 0.2629374604305027,
        "overall_raw": 0.2629374604305027,
        "tokens": 12120000,
        "wall_clock_hours": 5.25
      },
      {
        "checkpoint_id": 23,
        "commit_sha": "2c3e00fa44febf21255c19efb6f2ae00fab5872e",
        "kind": "auto-save",
        "overall": 0.2629374604305027,
        "overall_raw": 0.2629374604305027,
        "tokens": 12580000,
        "wall_clock_hours": 5.5
      },
      {
        "checkpoint_id": 24,
        "commit_sha": "f60d6f5f3548118819418d316933876ac740baa1",
        "kind": "auto-save",
        "overall": 0.26101711152048485,
        "overall_raw": 0.26101711152048485,
        "tokens": 13010000,
        "wall_clock_hours": 5.75
      },
      {
        "checkpoint_id": 26,
        "commit_sha": "51e036b20486061f42d8715ff08eb3a404de8f26",
        "kind": "auto-save",
        "overall": 0.23937102947322267,
        "overall_raw": 0.23937102947322267,
        "tokens": 13900000,
        "wall_clock_hours": 6.052222222222222
      },
      {
        "checkpoint_id": 27,
        "commit_sha": "0f10ca3cade7c437a3e383b215e6c611e30f719c",
        "kind": "auto-save",
        "overall": 0.2396102885164484,
        "overall_raw": 0.2396102885164484,
        "tokens": 14430000,
        "wall_clock_hours": 6.302222222222222
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "1e77fc0e61a277725001f6776b0a8b342cb99c65",
        "kind": "auto-save",
        "overall": 0.2396117345125729,
        "overall_raw": 0.2396117345125729,
        "tokens": 14980000,
        "wall_clock_hours": 6.552222222222222
      },
      {
        "checkpoint_id": 30,
        "commit_sha": "5fa29f002a66dadf8db577403c7a45249b79c3f0",
        "kind": "auto-save",
        "overall": 0.2396275567769241,
        "overall_raw": 0.2396275567769241,
        "tokens": 17900000,
        "wall_clock_hours": 7.052222222222222
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "267a3bc4ee959b62afd5920a6dd279a3c25bba10",
        "kind": "auto-save",
        "overall": 0.23963452543051,
        "overall_raw": 0.23963452543051,
        "tokens": 18550000,
        "wall_clock_hours": 7.302222222222222
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "7c064695ac27990e98e9625391267bc68a9158eb",
        "kind": "auto-save",
        "overall": 0.23964787471528504,
        "overall_raw": 0.23964787471528504,
        "tokens": 19860000,
        "wall_clock_hours": 7.552222222222222
      },
      {
        "checkpoint_id": 33,
        "commit_sha": "3820b2139b93b1a3a857a41b95c1ea0691cf1c5a",
        "kind": "auto-save",
        "overall": 0.4255691779135246,
        "overall_raw": 0.4255691779135246,
        "tokens": 21260000,
        "wall_clock_hours": 7.802222222222222
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "d7cddce06d34ab12f011785cd53412532d78cd84",
        "kind": "auto-save",
        "overall": 0.4251438608557629,
        "overall_raw": 0.4251438608557629,
        "tokens": 22810000,
        "wall_clock_hours": 8.302222222222222
      },
      {
        "checkpoint_id": 36,
        "commit_sha": "4fb1176b029bf6db56424ef78fe99616ef8a40ae",
        "kind": "auto-save",
        "overall": 0.42544362967136473,
        "overall_raw": 0.42544362967136473,
        "tokens": 24390000,
        "wall_clock_hours": 8.552222222222222
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "c2f78c0c43a0eea3cba627b70661befa7e2e211d",
        "kind": "auto-save",
        "overall": 0.42544362967136473,
        "overall_raw": 0.42544362967136473,
        "tokens": 26020000,
        "wall_clock_hours": 8.802222222222222
      },
      {
        "checkpoint_id": 38,
        "commit_sha": "2f577160f92d134facf7ff9a0be65a03ee7eb816",
        "kind": "auto-save",
        "overall": 0.42544362967136473,
        "overall_raw": 0.42544362967136473,
        "tokens": 27690000,
        "wall_clock_hours": 9.052222222222222
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "45ca286a1bfce076285b6c2c7043cc4503ce3a04",
        "kind": "auto-save",
        "overall": 0.4254437310646335,
        "overall_raw": 0.4254437310646335,
        "tokens": 30260000,
        "wall_clock_hours": 9.302222222222222
      },
      {
        "checkpoint_id": 42,
        "commit_sha": "7e900c9e4897f43dc0f1cb0c3966bc57d98f4963",
        "kind": "auto-save",
        "overall": 0.4254696660075208,
        "overall_raw": 0.4254696660075208,
        "tokens": 34110000,
        "wall_clock_hours": 10.052222222222222
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "1e954e84dc2efc4a5103f38828c7b0ca982c3b61",
        "kind": "auto-save",
        "overall": 0.4254696660075208,
        "overall_raw": 0.4254696660075208,
        "tokens": 34400000,
        "wall_clock_hours": 10.302222222222222
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "8c576cd22c7b886280eaddfdb0918377bbb26938",
        "kind": "auto-save",
        "overall": 0.4254696660075208,
        "overall_raw": 0.4254696660075208,
        "tokens": 34670000,
        "wall_clock_hours": 10.552222222222222
      },
      {
        "checkpoint_id": 45,
        "commit_sha": "fd47923395bb05796fc3daa18c5bb3f5efcf4244",
        "kind": "auto-save",
        "overall": 0.425469672693331,
        "overall_raw": 0.425469672693331,
        "tokens": 35250000,
        "wall_clock_hours": 10.802222222222222
      },
      {
        "checkpoint_id": 46,
        "commit_sha": "db6900d2c500d61aae37190fab4745754a1cb3eb",
        "kind": "auto-save",
        "overall": 0.425469672693331,
        "overall_raw": 0.425469672693331,
        "tokens": 35910000,
        "wall_clock_hours": 11.052222222222222
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "bbc9c62c8c8d3a4614ff15ed22837f869d16dbb0",
        "kind": "auto-save",
        "overall": 0.425469672693331,
        "overall_raw": 0.425469672693331,
        "tokens": 37000000,
        "wall_clock_hours": 11.302222222222222
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "50c160041c5e94499c8bea7ead28496f64dd5b3a",
        "kind": "auto-save",
        "overall": 0.425469672693331,
        "overall_raw": 0.425469672693331,
        "tokens": 37430000,
        "wall_clock_hours": 11.552222222222222
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "f571e97b11a658af1331282f0c2e5d968590362f",
        "kind": "auto-save",
        "overall": 0.42562555391315393,
        "overall_raw": 0.42562555391315393,
        "tokens": 38330000,
        "wall_clock_hours": 11.802222222222222
      },
      {
        "checkpoint_id": 50,
        "commit_sha": "04499e9a27b5e05bd1c2dff2c8d67284062e0340",
        "kind": "auto-save",
        "overall": 0.42562555391315393,
        "overall_raw": 0.42562555391315393,
        "tokens": 39750000,
        "wall_clock_hours": 12.052222222222222
      },
      {
        "checkpoint_id": 51,
        "commit_sha": "fd2e61edc2665798fa52b6fb2b4cb5c22a578e98",
        "kind": "auto-save",
        "overall": 0.4262035050830639,
        "overall_raw": 0.4262035050830639,
        "tokens": 40280000,
        "wall_clock_hours": 12.302222222222222
      },
      {
        "checkpoint_id": 52,
        "commit_sha": "5d11dacbc33c3b5c990a1fc70342f6ec1f1065b5",
        "kind": "auto-save",
        "overall": 0.42620369221905985,
        "overall_raw": 0.42620369221905985,
        "tokens": 41370000,
        "wall_clock_hours": 12.552222222222222
      },
      {
        "checkpoint_id": 53,
        "commit_sha": "c013995623d0bee4a06306ba05cf626924208819",
        "kind": "auto-save",
        "overall": 0.42620369221905985,
        "overall_raw": 0.42620369221905985,
        "tokens": 41970000,
        "wall_clock_hours": 12.802222222222222
      },
      {
        "checkpoint_id": 54,
        "commit_sha": "a1527ccd3e94483bbafd1d4d9a4bd5644616dc9d",
        "kind": "auto-save",
        "overall": 0.42620369221905985,
        "overall_raw": 0.42620369221905985,
        "tokens": 43190000,
        "wall_clock_hours": 13.052222222222222
      },
      {
        "checkpoint_id": 55,
        "commit_sha": "497574d63d8fb243fcaf42af895ec3cdd029022c",
        "kind": "auto-save",
        "overall": 0.42620369221905985,
        "overall_raw": 0.42620369221905985,
        "tokens": 44490000,
        "wall_clock_hours": 13.302222222222222
      },
      {
        "checkpoint_id": 56,
        "commit_sha": "8eeed8cf945283fbbb4f9542a4de63fd4bfe6022",
        "kind": "auto-save",
        "overall": 0.4262334150226188,
        "overall_raw": 0.4262334150226188,
        "tokens": 46500000,
        "wall_clock_hours": 13.552222222222222
      },
      {
        "checkpoint_id": 58,
        "commit_sha": "de7bf9d17643f4515247847197d35005145cc901",
        "kind": "auto-save",
        "overall": 0.4261770875052808,
        "overall_raw": 0.4261770875052808,
        "tokens": 48680000,
        "wall_clock_hours": 14.052222222222222
      },
      {
        "checkpoint_id": 59,
        "commit_sha": "873304f380b00f6242b9bdceeb88f350d533a590",
        "kind": "auto-save",
        "overall": 0.4380817605383424,
        "overall_raw": 0.4380817605383424,
        "tokens": 50190000,
        "wall_clock_hours": 14.302222222222222
      },
      {
        "checkpoint_id": 60,
        "commit_sha": "322b227341a0eb200d8f7b1aac5ca0768e63d32a",
        "kind": "auto-save",
        "overall": 0.4380817560863154,
        "overall_raw": 0.4380817560863154,
        "tokens": 52610000,
        "wall_clock_hours": 14.552222222222222
      },
      {
        "checkpoint_id": 61,
        "commit_sha": "fa4fea0785b729bbd4ff4f1fd45aee61a0e50a8b",
        "kind": "auto-save",
        "overall": 0.4380817560863154,
        "overall_raw": 0.4380817560863154,
        "tokens": 55080000,
        "wall_clock_hours": 14.802222222222222
      },
      {
        "checkpoint_id": 63,
        "commit_sha": "b6104e2a23c6733da8f16a2825b5b8d4ac3d0235",
        "kind": "auto-save",
        "overall": 0.4380817560863154,
        "overall_raw": 0.4380817560863154,
        "tokens": 60300000,
        "wall_clock_hours": 15.302222222222222
      },
      {
        "checkpoint_id": 64,
        "commit_sha": "7aaed935b02916f1772c27e77d3a1873756fc5f5",
        "kind": "auto-save",
        "overall": 0.4380817560863154,
        "overall_raw": 0.4380817560863154,
        "tokens": 62100000,
        "wall_clock_hours": 15.552222222222222
      },
      {
        "checkpoint_id": 65,
        "commit_sha": "62709caffa00551ff8dc995dbe719dff84d5e3a9",
        "kind": "auto-save",
        "overall": 0.4380817560863154,
        "overall_raw": 0.4380817560863154,
        "tokens": 63940000,
        "wall_clock_hours": 15.802222222222222
      },
      {
        "checkpoint_id": 66,
        "commit_sha": "3a285d459b1ffd1ca118b2552b310765c19b9eb9",
        "kind": "auto-save",
        "overall": 0.438083595902953,
        "overall_raw": 0.438083595902953,
        "tokens": 65819999,
        "wall_clock_hours": 16.052222222222223
      },
      {
        "checkpoint_id": 67,
        "commit_sha": "eeb58eac7e4a437708a306c096beb1922cda804b",
        "kind": "auto-save",
        "overall": 0.438083595902953,
        "overall_raw": 0.438083595902953,
        "tokens": 67000000,
        "wall_clock_hours": 16.302222222222223
      },
      {
        "checkpoint_id": 68,
        "commit_sha": "9bedac37d299751bf6921ea6a23df7098761a6c9",
        "kind": "auto-save",
        "overall": 0.438083595902953,
        "overall_raw": 0.438083595902953,
        "tokens": 67310000,
        "wall_clock_hours": 16.552222222222223
      },
      {
        "checkpoint_id": 69,
        "commit_sha": "27a4e3902f2aa905ff4be39bb0449d5cd0961233",
        "kind": "auto-save",
        "overall": 0.4381136273804963,
        "overall_raw": 0.4381136273804963,
        "tokens": 67630000,
        "wall_clock_hours": 16.802222222222223
      },
      {
        "checkpoint_id": 70,
        "commit_sha": "90d64d374a5d52888573bb8ada84be1ba1a9a413",
        "kind": "auto-save",
        "overall": 0.4381136273804963,
        "overall_raw": 0.4381136273804963,
        "tokens": 68250000,
        "wall_clock_hours": 17.052222222222223
      },
      {
        "checkpoint_id": 71,
        "commit_sha": "a0c7212abeb84624ad4d1be36e378e53b313209e",
        "kind": "auto-save",
        "overall": 0.4381136273804963,
        "overall_raw": 0.4381136273804963,
        "tokens": 69090000,
        "wall_clock_hours": 17.302222222222223
      },
      {
        "checkpoint_id": 72,
        "commit_sha": "871866543b66ba993349e87543b027542dfd63c4",
        "kind": "auto-save",
        "overall": 0.4381136273804963,
        "overall_raw": 0.4381136273804963,
        "tokens": 69590000,
        "wall_clock_hours": 17.552222222222223
      },
      {
        "checkpoint_id": 73,
        "commit_sha": "b5822324bea792adedf609a24286081b96e8a0c6",
        "kind": "auto-save",
        "overall": 0.4381136273804963,
        "overall_raw": 0.4381136273804963,
        "tokens": 70620000,
        "wall_clock_hours": 17.802222222222223
      },
      {
        "checkpoint_id": 74,
        "commit_sha": "4d07b37680b0dc2dcc57958f3885a31fb0a2ddc3",
        "kind": "auto-save",
        "overall": 0.4381136273804963,
        "overall_raw": 0.4381136273804963,
        "tokens": 71690000,
        "wall_clock_hours": 18.052222222222223
      },
      {
        "checkpoint_id": 76,
        "commit_sha": "ee9df308ed6dc4ab96159f0992911af61c73e4bb",
        "kind": "auto-save",
        "overall": 0.4381136343094756,
        "overall_raw": 0.4381136343094756,
        "tokens": 73490000,
        "wall_clock_hours": 18.552222222222223
      },
      {
        "checkpoint_id": 77,
        "commit_sha": "42be1438d89bb43cf759659f245cc8e183bf5a8b",
        "kind": "auto-save",
        "overall": 0.4381136343094756,
        "overall_raw": 0.4381136343094756,
        "tokens": 76360000,
        "wall_clock_hours": 18.802222222222223
      },
      {
        "checkpoint_id": 78,
        "commit_sha": "6764bb0f4f7b433dbeb068dfa6b33fbfce5d419b",
        "kind": "auto-save",
        "overall": 0.43811361876085897,
        "overall_raw": 0.43811361876085897,
        "tokens": 78580000,
        "wall_clock_hours": 19.052222222222223
      },
      {
        "checkpoint_id": 79,
        "commit_sha": "a53d09974a66776849b2b28401145d2d88a813aa",
        "kind": "auto-save",
        "overall": 0.43811361876085897,
        "overall_raw": 0.43811361876085897,
        "tokens": 80090000,
        "wall_clock_hours": 19.302222222222223
      }
    ],
    "wall_clock_hours": 19.302222222222223
  },
  {
    "baseline": false,
    "candidate": "gpt-5-4",
    "candidate_sha256": "076cfa1e8a40cafdca5501044f9d5ca93d069a8c05eaaa2175f651d136e76cad",
    "checkpoints_count": 69,
    "graded_at": "2026-05-12T08:15:51Z",
    "label": "GPT-5.4",
    "model": "gpt-5.4",
    "overall": 0.3160372478663838,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.7185044657095848e-11
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 3.3621455427701435e-11
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "bulletgba-gameplay": {
        "audio_score": 0.4415579439569347,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9358098859719997
      },
      "celeste-gameplay": {
        "audio_score": 0.6666413584112539,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.7247714103594585
      },
      "chip-advance-gameplay": {
        "audio_score": 0.8421764184672681,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9405218826372096
      },
      "collie-defense-gameplay": {
        "audio_score": 0.013496543569370674,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.0010892757610471975
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 1.0
      },
      "goodboy-gameplay": {
        "audio_score": 0.5769463097272912,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.991100533174756
      },
      "heartwrench-gameplay": {
        "audio_score": 0.00632230953647731,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.015456963682960302
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 6.8667075537947465e-12
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 4.1293673070903634e-7
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 1.0575712962127061e-7
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 6.682531772148243e-7
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 0.000017476977627496027
      },
      "piugba-gameplay": {
        "audio_score": 0.11758007878320267,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.3349403170561359
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 1.4636172764406895e-14
      },
      "spout-gameplay": {
        "audio_score": 0.09243714089538754,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.06153422466433488
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 2.706659188837667e-15
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 5.472195126567933e-13
      },
      "tonc-snd1": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.9662726391540158
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.3469022472819297,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.10791941844053568
      },
      "waimanu-gameplay": {
        "audio_score": 0.622031267141864,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.7830255857252684
      }
    },
    "provider": "OpenAI",
    "raw_overall": 0.4514817826662626,
    "realtime_note": "GPT-5.4's emulator runs slower than real-time (60fps for the GBA), with 7 of 11 replays over 16.67ms at the median. Its worst frames take around 50 ms which would look like a slideshow in real time. We give unlimited runtime so correctness can still be measured but we apply a 30% performance penalty.",
    "realtime_penalty": 0.3,
    "sections": {
      "audio": {
        "score": 0.3655045897072785,
        "subsystems": {
          "game_audio": 0.30992097018092285,
          "psg": 0.4210882092336341
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 0.2930564681801104,
        "subsystems": {
          "cpu": 0.5555575716979568,
          "dma": 0.5000002064683654,
          "halt_irq": 1.4636172764406895e-14,
          "memory": 5.28819981644122e-8,
          "timer": 2.749630859228155e-13
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.5329492851479748,
        "subsystems": {
          "gameplay": 0.5329492851479748
        },
        "weight": 0.6
      }
    },
    "tokens_used": 22430000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 1,
        "commit_sha": "38c6b3b5c33dabc0e72da34cb6a6bd96452d8c68",
        "kind": "auto-save",
        "overall": 0.003633131953150478,
        "overall_raw": 0.003633131953150478,
        "tokens": 232000,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 2,
        "commit_sha": "2010b68e6505b7a2b8e05a90b02c886d88dd9a04",
        "kind": "auto-save",
        "overall": 0.003633131953150478,
        "overall_raw": 0.003633131953150478,
        "tokens": 613000,
        "wall_clock_hours": 0.25
      },
      {
        "checkpoint_id": 3,
        "commit_sha": "a6aee71d338f96b2d85379189d92063ec358d86b",
        "kind": "auto-save",
        "overall": 0.15678021626925853,
        "overall_raw": 0.15678021626925853,
        "tokens": 613000,
        "wall_clock_hours": 0.5
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "ba19434ade762d5a34d8923b0ccf132fd0ee5cea",
        "kind": "auto-save",
        "overall": 0.15678021626925853,
        "overall_raw": 0.15678021626925853,
        "tokens": 1110000,
        "wall_clock_hours": 0.75
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "c760acc9767ee16aa339a16def3d5fc41ef8b41b",
        "kind": "auto-save",
        "overall": 0.2571505580267895,
        "overall_raw": 0.2571505580267895,
        "tokens": 1110000,
        "wall_clock_hours": 1.0
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "786a4431eb2cd879980e575bede6eec9c2e05c78",
        "kind": "auto-save",
        "overall": 0.2571505580267895,
        "overall_raw": 0.2571505580267895,
        "tokens": 1110000,
        "wall_clock_hours": 1.25
      },
      {
        "checkpoint_id": 7,
        "commit_sha": "ceb89e578c7c424fa29ea3b3b9fb1ab7226b4eb0",
        "kind": "auto-save",
        "overall": 0.2571505580267895,
        "overall_raw": 0.2571505580267895,
        "tokens": 1110000,
        "wall_clock_hours": 1.5
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "54b86fb05f895bc1ef9f556a6a07671bd77d8905",
        "kind": "auto-save",
        "overall": 0.2571505580267895,
        "overall_raw": 0.2571505580267895,
        "tokens": 1110000,
        "wall_clock_hours": 1.75
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "4aa02bbea6f5cb053df417e0a14655a767652740",
        "kind": "auto-save",
        "overall": 0.26966180768958964,
        "overall_raw": 0.26966180768958964,
        "tokens": 1110000,
        "wall_clock_hours": 2.0
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "ca118c7ba30302cd0cb29f7b6f7ba132a07810e3",
        "kind": "auto-save",
        "overall": 0.25609847347203846,
        "overall_raw": 0.25609847347203846,
        "tokens": 2820000,
        "wall_clock_hours": 2.25
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "383ee547dcb0e3a05e16f331f401c2c941c99bce",
        "kind": "auto-save",
        "overall": 0.2578668302451822,
        "overall_raw": 0.2578668302451822,
        "tokens": 2820000,
        "wall_clock_hours": 2.5
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "91f6996bc0f1444c79f7d4de595d6309c2f605c4",
        "kind": "auto-save",
        "overall": 0.2578668302451822,
        "overall_raw": 0.2578668302451822,
        "tokens": 2820000,
        "wall_clock_hours": 2.75
      },
      {
        "checkpoint_id": 13,
        "commit_sha": "7763b494f6f87600ff12792f30c2789b2353a85f",
        "kind": "auto-save",
        "overall": 0.2938251295328908,
        "overall_raw": 0.2938251295328908,
        "tokens": 2820000,
        "wall_clock_hours": 3.0
      },
      {
        "checkpoint_id": 14,
        "commit_sha": "2854aa9879f3a1d224fd1f92d95388f7a6ed08c1",
        "kind": "auto-save",
        "overall": 0.3162148817169471,
        "overall_raw": 0.3162148817169471,
        "tokens": 4230000,
        "wall_clock_hours": 3.25
      },
      {
        "checkpoint_id": 15,
        "commit_sha": "8bd6a3b775b7f1f7f7575b9a625e425dc3e24f62",
        "kind": "auto-save",
        "overall": 0.3158407832621286,
        "overall_raw": 0.3158407832621286,
        "tokens": 4770000,
        "wall_clock_hours": 3.5
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "4a57725855ba113a716a0201bea5dc42d9e16f89",
        "kind": "auto-save",
        "overall": 0.30928375106627487,
        "overall_raw": 0.30928375106627487,
        "tokens": 4930000,
        "wall_clock_hours": 3.75
      },
      {
        "checkpoint_id": 17,
        "commit_sha": "ea5311713d78446beae29790deafc66fb88c13eb",
        "kind": "auto-save",
        "overall": 0.30928375106627487,
        "overall_raw": 0.30928375106627487,
        "tokens": 4940000,
        "wall_clock_hours": 4.0
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "a56db11e4da8c0abb2f455b06a1e439b3a576c05",
        "kind": "auto-save",
        "overall": 0.3134261709056882,
        "overall_raw": 0.3134261709056882,
        "tokens": 5250000,
        "wall_clock_hours": 4.25
      },
      {
        "checkpoint_id": 19,
        "commit_sha": "3f9c98af9e17a7ac41460fabb30d75f43741c7a1",
        "kind": "auto-save",
        "overall": 0.31353050469939275,
        "overall_raw": 0.31353050469939275,
        "tokens": 5510000,
        "wall_clock_hours": 4.5
      },
      {
        "checkpoint_id": 20,
        "commit_sha": "b447bf25f58ecf237b5047ba2213cecfbe9a706d",
        "kind": "auto-save",
        "overall": 0.31353050469939275,
        "overall_raw": 0.31353050469939275,
        "tokens": 5820000,
        "wall_clock_hours": 4.75
      },
      {
        "checkpoint_id": 21,
        "commit_sha": "52f4d7f09c6b964f6178b1a03316832a326768bc",
        "kind": "auto-save",
        "overall": 0.3135279349388684,
        "overall_raw": 0.3135279349388684,
        "tokens": 6010000,
        "wall_clock_hours": 5.0
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "fa3f5059b9d919654870d665b3843d2f457378e7",
        "kind": "auto-save",
        "overall": 0.3135279349388684,
        "overall_raw": 0.3135279349388684,
        "tokens": 6440000,
        "wall_clock_hours": 5.25
      },
      {
        "checkpoint_id": 23,
        "commit_sha": "67c7749da8ea47039fd08a798c3f42b3955d6954",
        "kind": "auto-save",
        "overall": 0.31352840906885915,
        "overall_raw": 0.31352840906885915,
        "tokens": 6680000,
        "wall_clock_hours": 5.5
      },
      {
        "checkpoint_id": 25,
        "commit_sha": "5967d66b0b80bb1006fcb49a606f6824feeba7b3",
        "kind": "auto-save",
        "overall": 0.3136344513465698,
        "overall_raw": 0.3136344513465698,
        "tokens": 7020000,
        "wall_clock_hours": 5.795833333333333
      },
      {
        "checkpoint_id": 26,
        "commit_sha": "43dd759c140f28ca23884045041f378c4d1b68ba",
        "kind": "auto-save",
        "overall": 0.3137642951624495,
        "overall_raw": 0.3137642951624495,
        "tokens": 7030000,
        "wall_clock_hours": 6.045833333333333
      },
      {
        "checkpoint_id": 27,
        "commit_sha": "9b09d957cdb2fe4c4beda352aed10736c318b9e8",
        "kind": "auto-save",
        "overall": 0.31403570479268467,
        "overall_raw": 0.31403570479268467,
        "tokens": 7300000,
        "wall_clock_hours": 6.295833333333333
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "d7d6d303d9f96988ec9c0091d6edecad404910f1",
        "kind": "auto-save",
        "overall": 0.3140336368105027,
        "overall_raw": 0.3140336368105027,
        "tokens": 7530000,
        "wall_clock_hours": 6.545833333333333
      },
      {
        "checkpoint_id": 29,
        "commit_sha": "f3f4111634b78613f6c2e0b32dda0cb308e6a3da",
        "kind": "auto-save",
        "overall": 0.31428303835024635,
        "overall_raw": 0.31428303835024635,
        "tokens": 7530000,
        "wall_clock_hours": 6.795833333333333
      },
      {
        "checkpoint_id": 30,
        "commit_sha": "418d5cc78ca20c2b500491cd8ad4e4eda1f18a00",
        "kind": "auto-save",
        "overall": 0.3143112861512103,
        "overall_raw": 0.3143112861512103,
        "tokens": 7910000,
        "wall_clock_hours": 7.045833333333333
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "7abc63fbc441df4910d4e398eaf9795b9e311fd0",
        "kind": "auto-save",
        "overall": 0.3143153236066673,
        "overall_raw": 0.3143153236066673,
        "tokens": 7990000,
        "wall_clock_hours": 7.295833333333333
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "baabbff5ddbe49d6a3be2d29c2dab27e95db94eb",
        "kind": "auto-save",
        "overall": 0.31431246015942305,
        "overall_raw": 0.31431246015942305,
        "tokens": 8199999,
        "wall_clock_hours": 7.545833333333333
      },
      {
        "checkpoint_id": 33,
        "commit_sha": "21316b5f53106774709f989ad0f8f5a580d60611",
        "kind": "auto-save",
        "overall": 0.31437786854524125,
        "overall_raw": 0.31437786854524125,
        "tokens": 8300000,
        "wall_clock_hours": 7.795833333333333
      },
      {
        "checkpoint_id": 34,
        "commit_sha": "59be1b63a6a903de28d6cd155446a5a730f9c0cb",
        "kind": "auto-save",
        "overall": 0.31437984370318345,
        "overall_raw": 0.31437984370318345,
        "tokens": 8630000,
        "wall_clock_hours": 8.045833333333333
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "bad705c489e1c480b8b0f4ae4b32c37e3cc3030e",
        "kind": "auto-save",
        "overall": 0.3146415834720332,
        "overall_raw": 0.3146415834720332,
        "tokens": 8850000,
        "wall_clock_hours": 8.295833333333333
      },
      {
        "checkpoint_id": 36,
        "commit_sha": "25fcab99a39b57fc88874546f1405d717953a2e3",
        "kind": "auto-save",
        "overall": 0.31464090518546656,
        "overall_raw": 0.31464090518546656,
        "tokens": 9070000,
        "wall_clock_hours": 8.545833333333333
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "b9c70630d8a9521cf132668597af8f8325b31883",
        "kind": "auto-save",
        "overall": 0.3147589500233582,
        "overall_raw": 0.3147589500233582,
        "tokens": 9070000,
        "wall_clock_hours": 8.795833333333333
      },
      {
        "checkpoint_id": 38,
        "commit_sha": "2fc4c5c9cb091a41e94cf5ea76514dfe30bad468",
        "kind": "auto-save",
        "overall": 0.31475847011672614,
        "overall_raw": 0.31475847011672614,
        "tokens": 9250000,
        "wall_clock_hours": 9.045833333333333
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "9f506bc676fe7249b3c335b3cfd32eab5b98fe06",
        "kind": "auto-save",
        "overall": 0.3147774207604681,
        "overall_raw": 0.3147774207604681,
        "tokens": 9770000,
        "wall_clock_hours": 9.295833333333333
      },
      {
        "checkpoint_id": 40,
        "commit_sha": "60a0f91d5053169d726478944ae83caf853d115e",
        "kind": "auto-save",
        "overall": 0.31465874508434705,
        "overall_raw": 0.31465874508434705,
        "tokens": 9850000,
        "wall_clock_hours": 9.545833333333333
      },
      {
        "checkpoint_id": 41,
        "commit_sha": "15c3511ea9ec669c81cebf9385b17ad876dac2b2",
        "kind": "auto-save",
        "overall": 0.31465874508434705,
        "overall_raw": 0.31465874508434705,
        "tokens": 9900000,
        "wall_clock_hours": 9.795833333333333
      },
      {
        "checkpoint_id": 42,
        "commit_sha": "716f4c2a0fe7fdc550dea72f727f17147bc41d04",
        "kind": "auto-save",
        "overall": 0.31465874508434705,
        "overall_raw": 0.31465874508434705,
        "tokens": 10030000,
        "wall_clock_hours": 10.045833333333333
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "269f1b02fdd339c1683f84f827fcee2a43e9bb84",
        "kind": "auto-save",
        "overall": 0.31465874508434705,
        "overall_raw": 0.31465874508434705,
        "tokens": 10210000,
        "wall_clock_hours": 10.295833333333333
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "6d6069a2e6b0859110dbfe9a32338e76355bc7b6",
        "kind": "auto-save",
        "overall": 0.31465874508434705,
        "overall_raw": 0.31465874508434705,
        "tokens": 10450000,
        "wall_clock_hours": 10.545833333333333
      },
      {
        "checkpoint_id": 45,
        "commit_sha": "dde01b944dbf2e2056a61a81beb4ba9a38ca1b68",
        "kind": "auto-save",
        "overall": 0.3146639246056969,
        "overall_raw": 0.3146639246056969,
        "tokens": 10520000,
        "wall_clock_hours": 10.795833333333333
      },
      {
        "checkpoint_id": 46,
        "commit_sha": "8da50465924136b8a3bafa4420127ef9552fad5b",
        "kind": "auto-save",
        "overall": 0.31466246620248356,
        "overall_raw": 0.31466246620248356,
        "tokens": 11150000,
        "wall_clock_hours": 11.045833333333333
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "b41db39be9b53b54749395589d1697311a4b5c58",
        "kind": "auto-save",
        "overall": 0.3146653421250397,
        "overall_raw": 0.3146653421250397,
        "tokens": 11620000,
        "wall_clock_hours": 11.295833333333333
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "dc832fb5333007598ef802ddf6780f3af76cc1ce",
        "kind": "auto-save",
        "overall": 0.3146653421250397,
        "overall_raw": 0.3146653421250397,
        "tokens": 12180000,
        "wall_clock_hours": 11.545833333333333
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "478fc4b8e39deea3e0cf56268e6db6c52e3059d9",
        "kind": "auto-save",
        "overall": 0.3146653421250397,
        "overall_raw": 0.3146653421250397,
        "tokens": 12350000,
        "wall_clock_hours": 11.795833333333333
      },
      {
        "checkpoint_id": 51,
        "commit_sha": "bbbb2e49825dd33b39e1fb3ad25a54456b84920d",
        "kind": "auto-save",
        "overall": 0.31626965413317537,
        "overall_raw": 0.31626965413317537,
        "tokens": 12950000,
        "wall_clock_hours": 12.295833333333333
      },
      {
        "checkpoint_id": 52,
        "commit_sha": "97bcff6d12666dadf9ad41d8c0dfa8d8798ef48d",
        "kind": "auto-save",
        "overall": 0.316360622474951,
        "overall_raw": 0.316360622474951,
        "tokens": 13180000,
        "wall_clock_hours": 12.545833333333333
      },
      {
        "checkpoint_id": 76,
        "commit_sha": "9f390daa8f1bfefc756cd52d40b760b29df808fb",
        "kind": "auto-save",
        "overall": 0.31594871486245385,
        "overall_raw": 0.31594871486245385,
        "tokens": 18740000,
        "wall_clock_hours": 18.545833333333334
      },
      {
        "checkpoint_id": 78,
        "commit_sha": "4fea72eb395e2f98143b64839ce63f047e6f4ab0",
        "kind": "auto-save",
        "overall": 0.3159459547790843,
        "overall_raw": 0.3159459547790843,
        "tokens": 19070000,
        "wall_clock_hours": 19.045833333333334
      },
      {
        "checkpoint_id": 79,
        "commit_sha": "a2b4fcaec285bec158bc8561a6c7a167a14d8f9e",
        "kind": "auto-save",
        "overall": 0.31600790600259826,
        "overall_raw": 0.31600790600259826,
        "tokens": 19140000,
        "wall_clock_hours": 19.295833333333334
      },
      {
        "checkpoint_id": 80,
        "commit_sha": "a3100d5ad0fa5353608a86ed1238f4f579055f30",
        "kind": "auto-save",
        "overall": 0.31603688076696146,
        "overall_raw": 0.31603688076696146,
        "tokens": 19400000,
        "wall_clock_hours": 19.545833333333334
      },
      {
        "checkpoint_id": 81,
        "commit_sha": "6023929316a1dc03f10c0ffc79adb7e099966513",
        "kind": "auto-save",
        "overall": 0.3160376155589204,
        "overall_raw": 0.3160376155589204,
        "tokens": 19560000,
        "wall_clock_hours": 19.795833333333334
      },
      {
        "checkpoint_id": 82,
        "commit_sha": "dc2e1651afb8c5e5eddd4ac8dd9f31459048cfd8",
        "kind": "auto-save",
        "overall": 0.31606473060069473,
        "overall_raw": 0.31606473060069473,
        "tokens": 19950000,
        "wall_clock_hours": 20.045833333333334
      },
      {
        "checkpoint_id": 83,
        "commit_sha": "1008d7dd5a20567dc52c5c15d0f5c8a52da06d41",
        "kind": "auto-save",
        "overall": 0.31606473060069473,
        "overall_raw": 0.31606473060069473,
        "tokens": 20350000,
        "wall_clock_hours": 20.295833333333334
      },
      {
        "checkpoint_id": 84,
        "commit_sha": "5fa4e8583af6fcd6999402ee60588a15637bb6a9",
        "kind": "auto-save",
        "overall": 0.31606473060069473,
        "overall_raw": 0.31606473060069473,
        "tokens": 20590000,
        "wall_clock_hours": 20.545833333333334
      },
      {
        "checkpoint_id": 85,
        "commit_sha": "98bffa1b9d0fc45ced93d302a39337608af9de62",
        "kind": "auto-save",
        "overall": 0.315977570358559,
        "overall_raw": 0.315977570358559,
        "tokens": 20870000,
        "wall_clock_hours": 20.795833333333334
      },
      {
        "checkpoint_id": 86,
        "commit_sha": "46741ab86e4e2fc3475e5aaadfd62ee5ca9c6ef3",
        "kind": "auto-save",
        "overall": 0.31598148183253877,
        "overall_raw": 0.31598148183253877,
        "tokens": 20930000,
        "wall_clock_hours": 21.045833333333334
      },
      {
        "checkpoint_id": 87,
        "commit_sha": "c9a8e4af8a616548b61fbf401f44c84c556b5a0f",
        "kind": "auto-save",
        "overall": 0.3160288056749659,
        "overall_raw": 0.3160288056749659,
        "tokens": 21350000,
        "wall_clock_hours": 21.295833333333334
      },
      {
        "checkpoint_id": 88,
        "commit_sha": "e6a57b81dc31aa718f432bcdb7fc638fbb34f8f8",
        "kind": "auto-save",
        "overall": 0.31603073656977737,
        "overall_raw": 0.31603073656977737,
        "tokens": 21850000,
        "wall_clock_hours": 21.545833333333334
      },
      {
        "checkpoint_id": 89,
        "commit_sha": "dda81ac92debc7e2fcb6f23f0e3c9980a2464749",
        "kind": "auto-save",
        "overall": 0.3160309559800823,
        "overall_raw": 0.3160309559800823,
        "tokens": 21850000,
        "wall_clock_hours": 21.795833333333334
      },
      {
        "checkpoint_id": 90,
        "commit_sha": "a61f189aa5f4a888b4e8d0b846aeb11514098be0",
        "kind": "auto-save",
        "overall": 0.3160259307620294,
        "overall_raw": 0.3160259307620294,
        "tokens": 21850000,
        "wall_clock_hours": 22.045833333333334
      },
      {
        "checkpoint_id": 91,
        "commit_sha": "5052a2e5b8bc959d1d465bbbf0576ba1b20dcb64",
        "kind": "auto-save",
        "overall": 0.3160497468073947,
        "overall_raw": 0.3160497468073947,
        "tokens": 22200000,
        "wall_clock_hours": 22.295833333333334
      },
      {
        "checkpoint_id": 92,
        "commit_sha": "286361e644dcc76e8aded18f3f082e94635332ac",
        "kind": "auto-save",
        "overall": 0.31605576990725887,
        "overall_raw": 0.31605576990725887,
        "tokens": 22240000,
        "wall_clock_hours": 22.545833333333334
      },
      {
        "checkpoint_id": 93,
        "commit_sha": "6a5da00920f3b29d7d88aaa1366600a9acef40c4",
        "kind": "auto-save",
        "overall": 0.31602829839367813,
        "overall_raw": 0.31602829839367813,
        "tokens": 22360000,
        "wall_clock_hours": 22.795833333333334
      },
      {
        "checkpoint_id": 94,
        "commit_sha": "db73b777542efc2bde562796ce6afa6669af003f",
        "kind": "auto-save",
        "overall": 0.31603724786638376,
        "overall_raw": 0.31603724786638376,
        "tokens": 22420000,
        "wall_clock_hours": 23.045833333333334
      },
      {
        "checkpoint_id": 95,
        "commit_sha": "77121c02ae8315c0ddd89673375d0de3eff06da7",
        "kind": "auto-save",
        "overall": 0.31603724786638376,
        "overall_raw": 0.31603724786638376,
        "tokens": 22430000,
        "wall_clock_hours": 23.295833333333334
      }
    ],
    "wall_clock_hours": 23.295833333333334
  },
  {
    "baseline": false,
    "candidate": "goose-gemini-3-5-flash",
    "candidate_sha256": "0d3698f3b0df4ee5558931e27d55afb70fe415fe31226c7c30b7c5c066c85282",
    "checkpoints_count": 46,
    "graded_at": "2026-05-20T22:54:11Z",
    "label": "Gemini 3.5 Flash",
    "model": "google/gemini-3.5-flash",
    "overall": 0.06701366402557543,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 2.0924942716332466e-12
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.3527475366583153e-12
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 2.2077092753635552e-10
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 1.0
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.9240018345985e-9
      },
      "bulletgba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.2001538893372402
      },
      "celeste-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.0003147704966493561
      },
      "chip-advance-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.08212489514867731
      },
      "collie-defense-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.001089278597856039
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 9.999998989515044e-17
      },
      "goodboy-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.021473237632253235
      },
      "heartwrench-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.015456963682960302
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 1.0
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 8.155386339429605e-16
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 5.167991093617938e-16
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 2.0527446314852993e-14
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 3.0870159843998655e-14
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 6.0895625863417394e-15
      },
      "piugba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.020384297900952104
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 9.999998989515044e-17
      },
      "spout-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.062439741081784864
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 9.999998989515044e-17
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 9.999998989515044e-17
      },
      "tonc-snd1": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.0002503112556638808
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.00593467491898452
      },
      "waimanu-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.11873029712553992
      }
    },
    "provider": "Google",
    "sections": {
      "audio": {
        "score": 0.0,
        "subsystems": {
          "game_audio": 0.0,
          "psg": 0.0
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 0.19097222271554215,
        "subsystems": {
          "cpu": 0.22222222334980624,
          "dma": 3.0839954962847213e-16,
          "halt_irq": 9.999998989515044e-17,
          "memory": 0.5000000000000102,
          "timer": 9.999998989515044e-17
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.048032032470778335,
        "subsystems": {
          "gameplay": 0.048032032470778335
        },
        "weight": 0.6
      }
    },
    "tokens_used": 2352560000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 2,
        "commit_sha": "476fd9b2ed551d1b7629d7dd6258f99711a244fd",
        "kind": "auto-save",
        "overall": 0.007970005056076831,
        "overall_raw": 0.007970005056076831,
        "tokens": 16890000,
        "wall_clock_hours": 0.38333333333333336
      },
      {
        "checkpoint_id": 3,
        "commit_sha": "8c4aa7a9b4d5806ff4c8f59d12c30757d18d4e9a",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 58500000,
        "wall_clock_hours": 0.6666666666666666
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "70b2c735ee2f906dde0c8d50be352b999ebcdea5",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 124820000,
        "wall_clock_hours": 0.9666666666666668
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "73a9432a2fb7b3fa189ffd2d1529d27d40ab2adc",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 164070000,
        "wall_clock_hours": 1.2833333333333334
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "001f462df442deb110f9045c77e3121b029d6c1a",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 246310000,
        "wall_clock_hours": 1.5333333333333334
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "d5b4deb563371f78c9c8d7952ac8e509ddf9eb3c",
        "kind": "auto-save",
        "overall": 0.005434706824818055,
        "overall_raw": 0.005434706824818055,
        "tokens": 338050000,
        "wall_clock_hours": 1.8666666666666667
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "e1e171242f8ab17033d9c4f28ea6d9b3e22ef117",
        "kind": "auto-save",
        "overall": 0.005434247398572286,
        "overall_raw": 0.005434247398572286,
        "tokens": 366650000,
        "wall_clock_hours": 2.433333333333333
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "d52381d346cd73ed0106084f897aeab015935a12",
        "kind": "auto-save",
        "overall": 0.005434247398572286,
        "overall_raw": 0.005434247398572286,
        "tokens": 366650000,
        "wall_clock_hours": 2.683333333333333
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "10986cbbcdb0be520ce9b283c8112abe39398712",
        "kind": "auto-save",
        "overall": 0.005434247398572286,
        "overall_raw": 0.005434247398572286,
        "tokens": 366650000,
        "wall_clock_hours": 2.9833333333333334
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "8a9bc2455b908b519d7e867d10b4b6594ce10346",
        "kind": "auto-save",
        "overall": 0.005434706824818055,
        "overall_raw": 0.005434706824818055,
        "tokens": 395570000,
        "wall_clock_hours": 3.75
      },
      {
        "checkpoint_id": 13,
        "commit_sha": "b8e32a9daa87fc9d7db760e6459453ab7388f356",
        "kind": "auto-save",
        "overall": 0.008892261507302737,
        "overall_raw": 0.008892261507302737,
        "tokens": 483860000,
        "wall_clock_hours": 4.016666666666667
      },
      {
        "checkpoint_id": 14,
        "commit_sha": "d60d87087ffe8aab709041b5c6c9c0c40a4f190e",
        "kind": "auto-save",
        "overall": 0.008892261507302737,
        "overall_raw": 0.008892261507302737,
        "tokens": 568180000,
        "wall_clock_hours": 4.316666666666666
      },
      {
        "checkpoint_id": 15,
        "commit_sha": "6b2071281780648ceceec0dae581383411eae89d",
        "kind": "auto-save",
        "overall": 0.008892261507302737,
        "overall_raw": 0.008892261507302737,
        "tokens": 568180000,
        "wall_clock_hours": 4.566666666666666
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "a1eaf823ccf098ad4540335eede04a43cdfdd9b8",
        "kind": "auto-save",
        "overall": 0.008892261507302737,
        "overall_raw": 0.008892261507302737,
        "tokens": 568180000,
        "wall_clock_hours": 4.816666666666666
      },
      {
        "checkpoint_id": 17,
        "commit_sha": "68f6fb02469b51ad08a843498d6e8e36d69c847a",
        "kind": "auto-save",
        "overall": 0.008892261507302737,
        "overall_raw": 0.008892261507302737,
        "tokens": 568180000,
        "wall_clock_hours": 5.066666666666666
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "6cac15c7c12e4b07646112999676d894320a9682",
        "kind": "auto-save",
        "overall": 0.008892261507302737,
        "overall_raw": 0.008892261507302737,
        "tokens": 568180000,
        "wall_clock_hours": 5.316666666666666
      },
      {
        "checkpoint_id": 20,
        "commit_sha": "c215b7e29f3e4a1b4107ab19a8db431d1a7a5e84",
        "kind": "auto-save",
        "overall": 0.008892261507302737,
        "overall_raw": 0.008892261507302737,
        "tokens": 590740000,
        "wall_clock_hours": 5.716666666666667
      },
      {
        "checkpoint_id": 21,
        "commit_sha": "911bf876d0695bb5e965eb3116b41995e67c3119",
        "kind": "auto-save",
        "overall": 0.03806369464392843,
        "overall_raw": 0.03806369464392843,
        "tokens": 631230000,
        "wall_clock_hours": 5.966666666666667
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "79359b63e3eb87812eca5a77588da5de99689db8",
        "kind": "auto-save",
        "overall": 0.051845065121974274,
        "overall_raw": 0.051845065121974274,
        "tokens": 685620000,
        "wall_clock_hours": 6.4
      },
      {
        "checkpoint_id": 23,
        "commit_sha": "89ba5ce73857b8232eb7c8512991e46e84e25924",
        "kind": "auto-save",
        "overall": 0.051845065121974274,
        "overall_raw": 0.051845065121974274,
        "tokens": 759830000,
        "wall_clock_hours": 6.65
      },
      {
        "checkpoint_id": 24,
        "commit_sha": "0e96ce4ced09a1589bbb6eed8f5842e359b6fa22",
        "kind": "auto-save",
        "overall": 0.051845065121974274,
        "overall_raw": 0.051845065121974274,
        "tokens": 862590000,
        "wall_clock_hours": 6.916666666666667
      },
      {
        "checkpoint_id": 25,
        "commit_sha": "522cafde40beb898068fdd40dfe0e06aa424a777",
        "kind": "auto-save",
        "overall": 0.051845065121974274,
        "overall_raw": 0.051845065121974274,
        "tokens": 980870000,
        "wall_clock_hours": 7.166666666666667
      },
      {
        "checkpoint_id": 26,
        "commit_sha": "75c548bcddd13376ab3dcf833eff186410ca2a9f",
        "kind": "auto-save",
        "overall": 0.051845065121974274,
        "overall_raw": 0.051845065121974274,
        "tokens": 1090110000,
        "wall_clock_hours": 7.416666666666667
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "96fd14939cfad1d32b55085868070736a796f72a",
        "kind": "auto-save",
        "overall": 0.05184498073316524,
        "overall_raw": 0.05184498073316524,
        "tokens": 1181450000,
        "wall_clock_hours": 7.716666666666667
      },
      {
        "checkpoint_id": 29,
        "commit_sha": "c6a0e732ad4ae7b627f6d48474ecc7a9f6bae4b7",
        "kind": "auto-save",
        "overall": 0.05184498073316524,
        "overall_raw": 0.05184498073316524,
        "tokens": 1199230000,
        "wall_clock_hours": 7.966666666666667
      },
      {
        "checkpoint_id": 30,
        "commit_sha": "a781fc9279ef11e76d885e0a2fbe0e5607510d64",
        "kind": "auto-save",
        "overall": 0.05183395110873465,
        "overall_raw": 0.05183395110873465,
        "tokens": 1225480000,
        "wall_clock_hours": 8.216666666666667
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "3ee85855529f1d135e26d51b0f878556b9154d6b",
        "kind": "auto-save",
        "overall": 0.05184498073316524,
        "overall_raw": 0.05184498073316524,
        "tokens": 1243690000,
        "wall_clock_hours": 8.466666666666667
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "9fe66f5fb1d4c8e7f4253d9f2596e838208428ec",
        "kind": "auto-save",
        "overall": 0.06898929284913888,
        "overall_raw": 0.06898929284913888,
        "tokens": 1285740000,
        "wall_clock_hours": 8.716666666666667
      },
      {
        "checkpoint_id": 33,
        "commit_sha": "9e2592824d710b0dd5070f75608d8cceedebaab8",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1342530000,
        "wall_clock_hours": 8.966666666666667
      },
      {
        "checkpoint_id": 34,
        "commit_sha": "4a65f5d1e489d83b05c531dfe0b1b25eda36a1ac",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1406320000,
        "wall_clock_hours": 9.216666666666669
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "a31bc1cdb49b504842b4e1c5d080f50958b0015d",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1455300000,
        "wall_clock_hours": 11.033333333333331
      },
      {
        "checkpoint_id": 36,
        "commit_sha": "8e623eb13451dbfb49885544b7b432cd057ad411",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1506480000,
        "wall_clock_hours": 13.083333333333334
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "f9dff3c2b6488cdf4b6a766f9aed016cbed3343f",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1552420000,
        "wall_clock_hours": 14.85
      },
      {
        "checkpoint_id": 38,
        "commit_sha": "298de1b7427ff1a0377ee14e7a5d15ea37970c93",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1612910000,
        "wall_clock_hours": 15.383333333333333
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "a83766199f17961ae5683abe9e90c06de759d726",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1678540000,
        "wall_clock_hours": 15.633333333333333
      },
      {
        "checkpoint_id": 40,
        "commit_sha": "afd97c512c60af3d29388e25716aac24362fe865",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1744170000,
        "wall_clock_hours": 15.883333333333333
      },
      {
        "checkpoint_id": 41,
        "commit_sha": "6cac7d591af4e1ace0f4ed018f7f8056c34b8a2b",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1812360000,
        "wall_clock_hours": 16.133333333333333
      },
      {
        "checkpoint_id": 42,
        "commit_sha": "88e87903abcc373eb6685e4177b705bbff287a5c",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1868130000,
        "wall_clock_hours": 17.633333333333333
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "b3b645107798b22ac05a6c057638e8445cc9b05a",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1926760000,
        "wall_clock_hours": 18.566666666666663
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "79712c272091b4d8e5a74adb005ee3723a8ee0f0",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 1983700000,
        "wall_clock_hours": 19.15
      },
      {
        "checkpoint_id": 45,
        "commit_sha": "c7164b832a68e83df1d5372e765b9352ac6318a3",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 2045970000,
        "wall_clock_hours": 19.4
      },
      {
        "checkpoint_id": 46,
        "commit_sha": "d026b82971c500aeb6f6bb0993ec6e5185aeca87",
        "kind": "auto-save",
        "overall": 0.06705656808173481,
        "overall_raw": 0.06705656808173481,
        "tokens": 2108340000,
        "wall_clock_hours": 19.65
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "ec2a4c5395016081479b6789697ad463c1dd35bb",
        "kind": "auto-save",
        "overall": 0.06705656808785773,
        "overall_raw": 0.06705656808785773,
        "tokens": 2174710000,
        "wall_clock_hours": 19.916666666666668
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "6ae8977b023a2feecc36bdbb511138257cf20d30",
        "kind": "auto-save",
        "overall": 0.06705656808785773,
        "overall_raw": 0.06705656808785773,
        "tokens": 2236710000,
        "wall_clock_hours": 20.183333333333337
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "d336949c735cc69e662cb6bd56967839dea57ba9",
        "kind": "auto-save",
        "overall": 0.06705656808785773,
        "overall_raw": 0.06705656808785773,
        "tokens": 2297110000,
        "wall_clock_hours": 20.433333333333337
      },
      {
        "checkpoint_id": 50,
        "commit_sha": "3464e17cd3be10d7104ce35219e6875cb46c0417",
        "kind": "auto-save",
        "overall": 0.06701366402557543,
        "overall_raw": 0.06701366402557543,
        "tokens": 2352560000,
        "wall_clock_hours": 20.733333333333334
      }
    ],
    "wall_clock_hours": 20.733333333333334
  },
  {
    "baseline": false,
    "candidate": "goose-kimi-k2-6",
    "candidate_sha256": "2dee6cf89d510e726151123025a51cb94ab358cfbca68fa3bb0d71208a15b87b",
    "checkpoints_count": 133,
    "graded_at": "2026-05-01T19:36:37Z",
    "has_wasm": true,
    "label": "Kimi K2.6",
    "model": "moonshotai/kimi-k2.6",
    "overall": 0.008624932115315736,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "bulletgba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.014066221317839913
      },
      "celeste-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.00833802001542501
      },
      "chip-advance-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.01775700611898927
      },
      "collie-defense-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.0001557143365695708
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 9.999998989515044e-17
      },
      "goodboy-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.014958767220899654
      },
      "heartwrench-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.042487700097172
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 9.999998989515044e-17
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 9.999998989515044e-17
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 9.999998989515044e-17
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "piugba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.017286669414108866
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 9.999998989515044e-17
      },
      "spout-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.01114800589734716
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 9.999998989515044e-17
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 9.999998989515044e-17
      },
      "tonc-snd1": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.000048101474450216
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.03162959056739235
      },
      "waimanu-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.0002479589872607878
      }
    },
    "provider": "OpenRouter via goose",
    "sections": {
      "audio": {
        "score": 0.0,
        "subsystems": {
          "game_audio": 0.0,
          "psg": 0.0
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 9.999998989515044e-17,
        "subsystems": {
          "cpu": 9.999998989515044e-17,
          "dma": 9.999998989515044e-17,
          "halt_irq": 9.999998989515044e-17,
          "memory": 9.999998989515044e-17,
          "timer": 9.999998989515044e-17
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.014374886858859529,
        "subsystems": {
          "gameplay": 0.014374886858859529
        },
        "weight": 0.6
      }
    },
    "tokens_used": 59970000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 4,
        "commit_sha": "c86c3b44a3ed2a9e2068d64396f202b51da311c2",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 356000,
        "wall_clock_hours": 0.75
      },
      {
        "checkpoint_id": 5,
        "commit_sha": "d50253b64f9664bdcc54648a0a294f3d4039356a",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 601000,
        "wall_clock_hours": 1.0
      },
      {
        "checkpoint_id": 6,
        "commit_sha": "0356a06f004d9267beaa7be4d23816c16a9cacdf",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 660000,
        "wall_clock_hours": 1.25
      },
      {
        "checkpoint_id": 7,
        "commit_sha": "c78c1cb8b12c52886bef7288f68ef1b38053fe2b",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 842000,
        "wall_clock_hours": 1.5
      },
      {
        "checkpoint_id": 8,
        "commit_sha": "c1f9c7c1132f1c6565196f7bb0b91c9232edc4b0",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 876000,
        "wall_clock_hours": 1.75
      },
      {
        "checkpoint_id": 9,
        "commit_sha": "853a2f85392ef0948fdb2a875f9f40ab7042b682",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 1140000,
        "wall_clock_hours": 2.0
      },
      {
        "checkpoint_id": 10,
        "commit_sha": "abc1ff115bc99281c165b4c54b2df1d2fa06ca02",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 1380000,
        "wall_clock_hours": 2.25
      },
      {
        "checkpoint_id": 11,
        "commit_sha": "c3b61b4cc410a8664e182413c63822a9c03034a2",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 1550000,
        "wall_clock_hours": 2.5
      },
      {
        "checkpoint_id": 12,
        "commit_sha": "de144ac32a2d9e887e450977c2b1119139ae2df6",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2220000,
        "wall_clock_hours": 2.75
      },
      {
        "checkpoint_id": 13,
        "commit_sha": "daa3c9e28ab9137be5caff2ead154ee5bf5170c8",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2410000,
        "wall_clock_hours": 3.0
      },
      {
        "checkpoint_id": 14,
        "commit_sha": "da4032a1d322055fdfe112c63ee1ba385250d5a2",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2470000,
        "wall_clock_hours": 3.25
      },
      {
        "checkpoint_id": 15,
        "commit_sha": "460f0892875824f1cfdf447040a1d87f41c00a09",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2470000,
        "wall_clock_hours": 3.5
      },
      {
        "checkpoint_id": 16,
        "commit_sha": "59faf9c3cd4ba9d94bb78067fe9504260148a42e",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2470000,
        "wall_clock_hours": 3.75
      },
      {
        "checkpoint_id": 17,
        "commit_sha": "3c37333ad863ca058019c3870e660b4753e36d8b",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2540000,
        "wall_clock_hours": 4.0
      },
      {
        "checkpoint_id": 18,
        "commit_sha": "0ad866e78d97ebc9deafc0f4c80d4f7b8cee3cd3",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2540000,
        "wall_clock_hours": 4.25
      },
      {
        "checkpoint_id": 19,
        "commit_sha": "4a1c4327301a8cd753a7e0488052ba1518c53c76",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2540000,
        "wall_clock_hours": 4.5
      },
      {
        "checkpoint_id": 20,
        "commit_sha": "405f4f87028af9eeae762c7f94d9c7e0189a311c",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2610000,
        "wall_clock_hours": 4.75
      },
      {
        "checkpoint_id": 21,
        "commit_sha": "f69f8729339df81b9a28a14f00a642f8fb1976a4",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2970000,
        "wall_clock_hours": 5.0
      },
      {
        "checkpoint_id": 22,
        "commit_sha": "f9bfa299a26cd2f3c08c04bff1400a8c9dbf45d3",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 2970000,
        "wall_clock_hours": 5.25
      },
      {
        "checkpoint_id": 24,
        "commit_sha": "558852e0290e820cc6745e314362c3241d236ebd",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 5220000,
        "wall_clock_hours": 5.75
      },
      {
        "checkpoint_id": 25,
        "commit_sha": "a6bfc62634017619d74a40472dafe9f0837be302",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 5780000,
        "wall_clock_hours": 6.0
      },
      {
        "checkpoint_id": 26,
        "commit_sha": "0a76a5c4f62ca5ee66fc1e602f9f5e502d16fbdc",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 5880000,
        "wall_clock_hours": 6.25
      },
      {
        "checkpoint_id": 28,
        "commit_sha": "365d9bf6abe12a19cf4f6f565cd29683e3fe4d61",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 8840000,
        "wall_clock_hours": 6.75
      },
      {
        "checkpoint_id": 29,
        "commit_sha": "731eacd5d4ac557bb349dc22a7508ffef66d8df8",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 9170000,
        "wall_clock_hours": 7.0
      },
      {
        "checkpoint_id": 30,
        "commit_sha": "bbba689e00c9638045ff9dd1bb3acfc7fc35ccf4",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 9280000,
        "wall_clock_hours": 7.25
      },
      {
        "checkpoint_id": 31,
        "commit_sha": "7c978b7cc2bc03ed3b2920aeac38120d8312fd4d",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 9390000,
        "wall_clock_hours": 7.5
      },
      {
        "checkpoint_id": 32,
        "commit_sha": "3cdef1f25c0b99b28e7857ad6c091dc51b2e4830",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 10890000,
        "wall_clock_hours": 7.75
      },
      {
        "checkpoint_id": 33,
        "commit_sha": "73bd939a69baa1ead98840d8d40d433e687275b8",
        "kind": "auto-save",
        "overall": 0.008651057926188204,
        "overall_raw": 0.008651057926188204,
        "tokens": 11230000,
        "wall_clock_hours": 8.0
      },
      {
        "checkpoint_id": 34,
        "commit_sha": "d6846f7e674b18dddf3930a9d7d4aa845d2c1549",
        "kind": "auto-save",
        "overall": 0.008651057926188204,
        "overall_raw": 0.008651057926188204,
        "tokens": 11810000,
        "wall_clock_hours": 8.25
      },
      {
        "checkpoint_id": 35,
        "commit_sha": "2b38ddc9410cf9604efebbcb82473e19acd446a8",
        "kind": "auto-save",
        "overall": 0.008651057926188204,
        "overall_raw": 0.008651057926188204,
        "tokens": 12620000,
        "wall_clock_hours": 8.5
      },
      {
        "checkpoint_id": 36,
        "commit_sha": "2112662cb0a942e9cf655c819a1d917be250ff7b",
        "kind": "auto-save",
        "overall": 0.008651057926188204,
        "overall_raw": 0.008651057926188204,
        "tokens": 12620000,
        "wall_clock_hours": 8.75
      },
      {
        "checkpoint_id": 37,
        "commit_sha": "6aab69b435cbb64ff3b99a394cc2d56a1df0a4df",
        "kind": "auto-save",
        "overall": 0.007314540236312137,
        "overall_raw": 0.007314540236312137,
        "tokens": 13410000,
        "wall_clock_hours": 9.0
      },
      {
        "checkpoint_id": 38,
        "commit_sha": "3c09c46c3d86856fb585f6d6cac43d55ba2e7dfd",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 13940000,
        "wall_clock_hours": 9.25
      },
      {
        "checkpoint_id": 39,
        "commit_sha": "e426554011eba1bb7033baf43510d1c96961da29",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 15880000,
        "wall_clock_hours": 9.5
      },
      {
        "checkpoint_id": 40,
        "commit_sha": "dda99c0e741ded4a27b22ecf675bef42865c5b03",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 18800000,
        "wall_clock_hours": 9.75
      },
      {
        "checkpoint_id": 41,
        "commit_sha": "5bcbcb09134fd9ba3e4d9d26ac322eb1a29a1761",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 20020000,
        "wall_clock_hours": 10.0
      },
      {
        "checkpoint_id": 42,
        "commit_sha": "55acf15bba33b8d881834083ff0cffcebd253b75",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 21730000,
        "wall_clock_hours": 10.25
      },
      {
        "checkpoint_id": 43,
        "commit_sha": "db8f88093080bead42e9ef5c57da8436bc530db9",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 22050000,
        "wall_clock_hours": 10.5
      },
      {
        "checkpoint_id": 44,
        "commit_sha": "aecf75b1b55d71b04917d023b6d90e738905b68a",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 22050000,
        "wall_clock_hours": 10.75
      },
      {
        "checkpoint_id": 45,
        "commit_sha": "30934b839095795b42eda4ca04fdb8e97e41bc5e",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 22190000,
        "wall_clock_hours": 10.860555555555557
      },
      {
        "checkpoint_id": 46,
        "commit_sha": "284960342d8803b4a4c1fc098470424b3e196dbe",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 22620000,
        "wall_clock_hours": 11.110555555555557
      },
      {
        "checkpoint_id": 47,
        "commit_sha": "757d9877ec4c8bce92ec097593713dc8c4cd4028",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 23650000,
        "wall_clock_hours": 11.360555555555557
      },
      {
        "checkpoint_id": 48,
        "commit_sha": "6c9b1f1b7d86b304feac411bc47402b3004c99a8",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 25030000,
        "wall_clock_hours": 11.610555555555557
      },
      {
        "checkpoint_id": 49,
        "commit_sha": "457a670f0bc1e93613da0fe0c5bbb77edd067bae",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 28100000,
        "wall_clock_hours": 11.860555555555557
      },
      {
        "checkpoint_id": 50,
        "commit_sha": "001f777eae0243fe4022ac9409297cddc6c0d3be",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 32939999,
        "wall_clock_hours": 12.110555555555557
      },
      {
        "checkpoint_id": 52,
        "commit_sha": "c5a0d70cc365d3a97add4ec5248870161280149e",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 37360000,
        "wall_clock_hours": 12.610555555555557
      },
      {
        "checkpoint_id": 54,
        "commit_sha": "379f40289dc10883a2858ca43bac9f7ea866ad59",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 39920000,
        "wall_clock_hours": 13.110555555555557
      },
      {
        "checkpoint_id": 55,
        "commit_sha": "66f8f110cad7022a916bd67bcc8d7d06dd0076b3",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 40090000,
        "wall_clock_hours": 13.360555555555557
      },
      {
        "checkpoint_id": 56,
        "commit_sha": "848aa860e375d142cddc18b31a35c8bd4d175670",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 40310000,
        "wall_clock_hours": 13.610555555555557
      },
      {
        "checkpoint_id": 57,
        "commit_sha": "9ce53d8e9f0b1bcc99efa6a822ee08365d874583",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 40960000,
        "wall_clock_hours": 13.860555555555557
      },
      {
        "checkpoint_id": 58,
        "commit_sha": "3004fcead0c96d19632805b2299c165b45380d78",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 41460000,
        "wall_clock_hours": 14.110555555555557
      },
      {
        "checkpoint_id": 59,
        "commit_sha": "b19645bbc44226fe78c5be0f5887bb734e130af1",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 41710000,
        "wall_clock_hours": 14.360555555555557
      },
      {
        "checkpoint_id": 60,
        "commit_sha": "95e016fcd5a532f3b949e90bd2cc8de4aa103b5a",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 41900000,
        "wall_clock_hours": 14.610555555555557
      },
      {
        "checkpoint_id": 61,
        "commit_sha": "a0c48a149c9d7c5d48893be5834c100f5e6eb031",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 42340000,
        "wall_clock_hours": 14.860555555555557
      },
      {
        "checkpoint_id": 62,
        "commit_sha": "6a2bd65d2d3845109d885f6d52035fcce955be7f",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 42410000,
        "wall_clock_hours": 15.110555555555557
      },
      {
        "checkpoint_id": 63,
        "commit_sha": "9344e64212e138e544634523a7a18ffae8f2e453",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 42560000,
        "wall_clock_hours": 15.360555555555557
      },
      {
        "checkpoint_id": 64,
        "commit_sha": "0c4aed0d176eaa864c5d8a879dd3fae29783228c",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 42640000,
        "wall_clock_hours": 15.610555555555557
      },
      {
        "checkpoint_id": 65,
        "commit_sha": "60db8afd67796a65639877bc36b6ebd96654a1e9",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 42720000,
        "wall_clock_hours": 15.860555555555557
      },
      {
        "checkpoint_id": 66,
        "commit_sha": "152686b04837de96da46f7559f659d33ec9b6ff3",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43090000,
        "wall_clock_hours": 16.110555555555557
      },
      {
        "checkpoint_id": 67,
        "commit_sha": "eaf7d8da3b7ecac651a8bcd317cad5fae56aa94d",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43090000,
        "wall_clock_hours": 16.360555555555557
      },
      {
        "checkpoint_id": 68,
        "commit_sha": "72356efddd82aeed8fb685941ea999e1a6a6c03f",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43180000,
        "wall_clock_hours": 16.610555555555557
      },
      {
        "checkpoint_id": 69,
        "commit_sha": "9f16e389390ee41f107fc8e91024e0a46e3feec6",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43340000,
        "wall_clock_hours": 16.860555555555557
      },
      {
        "checkpoint_id": 70,
        "commit_sha": "2d64d077758d6bfca2d6220c966a0471319691f6",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43340000,
        "wall_clock_hours": 17.110555555555557
      },
      {
        "checkpoint_id": 71,
        "commit_sha": "859398380b3216487033ac8b2f2c65d845650601",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43510000,
        "wall_clock_hours": 17.360555555555557
      },
      {
        "checkpoint_id": 72,
        "commit_sha": "67ae0bd3ff0567817f82a011d01168781b041000",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43680000,
        "wall_clock_hours": 17.610555555555557
      },
      {
        "checkpoint_id": 73,
        "commit_sha": "b0050a8e371ffe1b38aae8119840b4990e50211e",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43780000,
        "wall_clock_hours": 17.860555555555557
      },
      {
        "checkpoint_id": 74,
        "commit_sha": "0281277974e3816aa0a0d3b9415c6b74fc694a15",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 43780000,
        "wall_clock_hours": 18.110555555555557
      },
      {
        "checkpoint_id": 75,
        "commit_sha": "dacf0feb86d2cb41f5d684278f2a27303010148b",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 44130000,
        "wall_clock_hours": 18.360555555555557
      },
      {
        "checkpoint_id": 76,
        "commit_sha": "85dc0d5adf925686f2d6615c272e49fcb1124c39",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 44730000,
        "wall_clock_hours": 18.610555555555557
      },
      {
        "checkpoint_id": 80,
        "commit_sha": "a1cff51a20e11abe145119f921d54eda11fa4956",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 47180000,
        "wall_clock_hours": 19.610555555555557
      },
      {
        "checkpoint_id": 81,
        "commit_sha": "9315c1e365fca914aca65cc2eda6592492f35bab",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 48190000,
        "wall_clock_hours": 19.860555555555557
      },
      {
        "checkpoint_id": 82,
        "commit_sha": "f34100264f92631fadb1fa4bb4d8e5a085daddfb",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 48610000,
        "wall_clock_hours": 20.110555555555557
      },
      {
        "checkpoint_id": 83,
        "commit_sha": "651344385c45d5160f79ed24497b112f0e352f6a",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 48940000,
        "wall_clock_hours": 20.360555555555557
      },
      {
        "checkpoint_id": 84,
        "commit_sha": "08bee84ee8a06c1107bb31a9c4747144f8aca16b",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 49390000,
        "wall_clock_hours": 20.610555555555557
      },
      {
        "checkpoint_id": 85,
        "commit_sha": "7c321035e8f2155b41058f74995ac81c6a0c5b04",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 50070000,
        "wall_clock_hours": 20.860555555555557
      },
      {
        "checkpoint_id": 86,
        "commit_sha": "7c351fb32bca6a71a094203632abbe49a06aa83c",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 50540000,
        "wall_clock_hours": 21.110555555555557
      },
      {
        "checkpoint_id": 87,
        "commit_sha": "cfc5c8492aa5f842709f4ca71e2fb821a7177c18",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 51160000,
        "wall_clock_hours": 21.360555555555557
      },
      {
        "checkpoint_id": 88,
        "commit_sha": "50d61b18878c5283ef3a026c7c20fb4f9e1cc8a1",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 52060000,
        "wall_clock_hours": 21.610555555555557
      },
      {
        "checkpoint_id": 89,
        "commit_sha": "cbbb0114e0de8e5f82b8c3ba8c4267ebf50f42d6",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 53390000,
        "wall_clock_hours": 21.860555555555557
      },
      {
        "checkpoint_id": 90,
        "commit_sha": "3103a2d956329e87b371d05b6757cc7c28745a1d",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 53680000,
        "wall_clock_hours": 22.110555555555557
      },
      {
        "checkpoint_id": 91,
        "commit_sha": "a5e6befdb14801458aa98d443b78e17dff09f053",
        "kind": "auto-save",
        "overall": 0.009505154054458606,
        "overall_raw": 0.009505154054458606,
        "tokens": 54830000,
        "wall_clock_hours": 22.360555555555557
      },
      {
        "checkpoint_id": 92,
        "commit_sha": "873ea584153c6ff00d96341875eaff467e47e690",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 55580000,
        "wall_clock_hours": 22.610555555555557
      },
      {
        "checkpoint_id": 93,
        "commit_sha": "9837e3dbd8a401a0df452fa9d65aee422295eea1",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 55880000,
        "wall_clock_hours": 22.860555555555557
      },
      {
        "checkpoint_id": 94,
        "commit_sha": "08f31ebde53ded90ea4e26d78913dab2b047a17c",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 56650000,
        "wall_clock_hours": 23.110555555555557
      },
      {
        "checkpoint_id": 95,
        "commit_sha": "6d125ee74e50e6ece4f394ca598d0f8082194140",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 58030000,
        "wall_clock_hours": 23.360555555555557
      },
      {
        "checkpoint_id": 96,
        "commit_sha": "dc4379b02bd745bf323061ed1a3eb2885e394dae",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 58350000,
        "wall_clock_hours": 23.610555555555557
      },
      {
        "checkpoint_id": 97,
        "commit_sha": "2afce4f476829bcfedf02a8737bb031aab00cecc",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59320000,
        "wall_clock_hours": 23.860555555555557
      },
      {
        "checkpoint_id": 98,
        "commit_sha": "33f0aaab62eb707a6a0292e0e85ca82c57ddd9e1",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59480000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 99,
        "commit_sha": "29675086c0192977900bd57142532431f085be3b",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 100,
        "commit_sha": "259b039df88f0abc15420d0865309c035b7bff1d",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 101,
        "commit_sha": "7017d3c95b2f555ecccc16a9c978ccc508c22787",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 102,
        "commit_sha": "74a8dab1fea83db17d4111194e83ed827a7a204d",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 103,
        "commit_sha": "c33d59966db44f68e143f54e7a79148fc956d2d5",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 104,
        "commit_sha": "0a6902b39cb36af795d761029d941405619a42a7",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 105,
        "commit_sha": "73641f7459847a8ab818516b1076b1f670f881cc",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 106,
        "commit_sha": "2b7abfc2da109448e9bb1516cb1d4aae6961a89a",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 107,
        "commit_sha": "8cbbcf5ea7d1320bbf980c9377a9ec907955073f",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 109,
        "commit_sha": "5578dc32d0836afa88dce7c76966d3e3d1ef11f6",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 110,
        "commit_sha": "1c60242ddf89114933ba0fefcb88ad309360964c",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 111,
        "commit_sha": "811c7e90bd465d9a34a11322b9514ea40d3787b2",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 112,
        "commit_sha": "f82c06a40440052d7fb8ad37c9ae8e8389b54809",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 113,
        "commit_sha": "054750fc6cbe96b911371d65ea18e914fdf8d92a",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 114,
        "commit_sha": "35f054935f685a68609632b9cde96caafa81e353",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 115,
        "commit_sha": "68bd4f504922f97a9c06f97d22d65c901ab5ea42",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 116,
        "commit_sha": "f84daba04f9a669a842c9dd4f8d14b514bc05636",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 117,
        "commit_sha": "331a76ca0786450a8cde00a9316d0b6392dd33bb",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 118,
        "commit_sha": "c17922d755515a40f61aca934de81c2f1f6f0414",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 120,
        "commit_sha": "7c8da1ddf56f81bbe331f1f0eaf2ef0743e29324",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 121,
        "commit_sha": "728291a64200ea73440bc832cee9ffd7a4b792be",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 122,
        "commit_sha": "d908e8366db74113489d0b00913f134654239406",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 123,
        "commit_sha": "d81551730481dd6aff99f6756c7c809654c393a7",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 124,
        "commit_sha": "35e58ed4081fcf573c0d7b65cebc6a3e580ee3bb",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 125,
        "commit_sha": "3f6b241b8d178807034f9fc0384f48317d0f7698",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 126,
        "commit_sha": "0d0d702f28aa70c7dae2821ecb31d5a0a416007a",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 127,
        "commit_sha": "a39403cc071c9ed8a8ea6f065b7ff4cd1e5ead66",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 128,
        "commit_sha": "7fbbe9617a30e16aa9a4b670efefddf49163fd2e",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 129,
        "commit_sha": "72b8e7790a9936ae8f9309d2281adfc9ce7a337f",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 130,
        "commit_sha": "1a25c71689552d097e70e7b3b74d3cfd152a98b0",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 131,
        "commit_sha": "2afa0ec480c526a55f61a767abe4bc0eda39861c",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 132,
        "commit_sha": "d310c364b552d79fa7164026df207a7eabbf114a",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 133,
        "commit_sha": "6c68bd13d1ca47e0ad07ed79e3623f3b66e4f404",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 134,
        "commit_sha": "2b12b12cdd004eb9e1af695f20255816f6f485ef",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 135,
        "commit_sha": "f2efbd1684fb85a7b1902dbbcbeb20a19fc70f82",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 136,
        "commit_sha": "c7dbc17f37d6856835b89e0d692c4c7be9909c9c",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 137,
        "commit_sha": "fc8ac6b9ee10db07352c2a9d07e0f2cc91c10ad0",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 138,
        "commit_sha": "d9b67a3bd71391dd4b8cb6c412e348499c298af8",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 139,
        "commit_sha": "2b9e4b16a33e7ea4b9a57173671123a10e018b16",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 140,
        "commit_sha": "6132cc2c0786ad19192533574a40430f3f049d70",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 141,
        "commit_sha": "22c59cad8561e58627fea9d7301ff0116766a5b5",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 142,
        "commit_sha": "c48fb67c6789bae7a8b8ded3f7b37aea0078adbc",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 143,
        "commit_sha": "7ccce48a3555ade0977822698149bd90c0814405",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 144,
        "commit_sha": "43d206480fa6b60573b90d2ef956ab43a7882b9d",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      },
      {
        "checkpoint_id": 145,
        "commit_sha": "4f53295236cbfc3aa606a324a2422aab7ee7457f",
        "kind": "auto-save",
        "overall": 0.008624932115315736,
        "overall_raw": 0.008624932115315736,
        "tokens": 59970000,
        "wall_clock_hours": 24.0
      }
    ],
    "wall_clock_hours": 24.0
  },
  {
    "baseline": false,
    "candidate": "gemini-pro",
    "candidate_sha256": "e430f6e792fcfda641068e2a0ade076b1099c53db0eae4b1aca29fcef0bffafe",
    "checkpoints_count": 1,
    "graded_at": "2026-05-03T08:44:20Z",
    "has_wasm": true,
    "label": "Gemini 3.1 Pro",
    "model": "gemini-3.1-pro-preview",
    "overall": 0.008462790979968672,
    "per_testcase": {
      "aw-arm-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-arm-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-arm-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-thumb-alu": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-thumb-ldm-stm": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "aw-thumb-ldr-str": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "bulletgba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.014066221317839913
      },
      "celeste-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.00833802001542501
      },
      "chip-advance-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.014784418637626397
      },
      "collie-defense-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.0001557143365695708
      },
      "dma-priority": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 9.999998989515044e-17
      },
      "goodboy-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.014958767220899654
      },
      "heartwrench-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.042487700097172
      },
      "memory": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 9.999998989515044e-17
      },
      "mgba-carry": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "mgba-dma": {
        "section": "procedural",
        "subsystem": "dma",
        "video_score": 9.999998989515044e-17
      },
      "mgba-io-read": {
        "section": "procedural",
        "subsystem": "memory",
        "video_score": 9.999998989515044e-17
      },
      "mgba-multiply-long": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "mgba-shifter": {
        "section": "procedural",
        "subsystem": "cpu",
        "video_score": 9.999998989515044e-17
      },
      "piugba-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.017286669414108866
      },
      "ppu-vram-mirror": {
        "section": "procedural",
        "subsystem": "halt_irq",
        "video_score": 9.999998989515044e-17
      },
      "spout-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.01114800589734716
      },
      "timer-reload": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 9.999998989515044e-17
      },
      "timer-start-stop": {
        "section": "procedural",
        "subsystem": "timer",
        "video_score": 9.999998989515044e-17
      },
      "tonc-snd1": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.000048101474450216
      },
      "varooom-3d-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.03162959056739235
      },
      "waimanu-gameplay": {
        "audio_score": 0.0,
        "section": "replay",
        "subsystem": "gameplay",
        "video_score": 0.0002479589872607878
      }
    },
    "provider": "Google",
    "sections": {
      "audio": {
        "score": 0.0,
        "subsystems": {
          "game_audio": 0.0,
          "psg": 0.0
        },
        "weight": 0.2
      },
      "procedural": {
        "score": 9.999998989515044e-17,
        "subsystems": {
          "cpu": 9.999998989515044e-17,
          "dma": 9.999998989515044e-17,
          "halt_irq": 9.999998989515044e-17,
          "memory": 9.999998989515044e-17,
          "timer": 9.999998989515044e-17
        },
        "weight": 0.2
      },
      "replay": {
        "score": 0.014104651633281085,
        "subsystems": {
          "gameplay": 0.014104651633281085
        },
        "weight": 0.6
      }
    },
    "tokens_used": 0,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      },
      {
        "checkpoint_id": 1,
        "commit_sha": "2ddd547822635bcb59a2abd4e4a043fef312ff3d",
        "kind": "auto-save",
        "overall": 0.008462790979968672,
        "overall_raw": 0.008462790979968672,
        "tokens": 0,
        "wall_clock_hours": 0.0
      }
    ],
    "wall_clock_hours": 0.0
  },
  {
    "baseline": false,
    "candidate": "goose-glm-5-1",
    "candidate_sha256": "",
    "checkpoints_count": 0,
    "failure_summary": {
      "build_failed": 2,
      "grading_failed": 143,
      "total": 145
    },
    "graded_at": "",
    "has_wasm": false,
    "label": "GLM 5.1",
    "model": "z-ai/glm-5.1",
    "overall": 0.0,
    "per_testcase": {},
    "provider": "OpenRouter via goose",
    "sections": {},
    "tokens_used": 5680000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      }
    ],
    "wall_clock_hours": 24.0
  },
  {
    "baseline": false,
    "candidate": "goose-minimax-m2-7",
    "candidate_sha256": "",
    "checkpoints_count": 0,
    "failure_summary": {
      "build_failed": 1,
      "grading_failed": 143,
      "total": 144
    },
    "graded_at": "",
    "has_wasm": false,
    "label": "MiniMax M2.7",
    "model": "minimax/minimax-m2.7",
    "overall": 0.0,
    "per_testcase": {},
    "provider": "OpenRouter via goose",
    "sections": {},
    "tokens_used": 191970000,
    "trajectory": [
      {
        "kind": "origin",
        "overall": 0.0,
        "tokens": 0,
        "wall_clock_hours": 0.0
      }
    ],
    "wall_clock_hours": 24.0
  }
]