{
  "model": "deepseek-v4-flash-0731",
  "reasoning_effort_claim": "not_proven_max; archived Desktop setting high and gateway transport omitted effort",
  "pins": {
    "desktop": "9922ff0a8c54b76fa53489ff68adcf5b3a25491d",
    "app": "167a0c21c92ba830db5e84d51400708b001cc53a",
    "harness": "f81872b413b83f65f4a0b7025ff2baa5554d3945",
    "factory_terminal": "318a52fff0c8b66c5ca265f41776ae522734305a"
  },
  "terminal_units": 60,
  "unique_tasks": 60,
  "verdicts": {
    "pass": 39,
    "fail": 17,
    "neutralized": 4
  },
  "cost": {
    "credits": 10935262,
    "requests": 2467,
    "input_tokens": 104023392,
    "cached_input_tokens": 65148928,
    "output_tokens": 1314500,
    "wasted_credits": 722722,
    "api_eur_operational_estimate": 43.631695,
    "infra_eur_measured_plus_prior_failure_conservative": 2.2766,
    "total_eur_operational_conservative": 45.908295,
    "authorized_cap_eur": 50.0
  },
  "durations_s": {
    "agent": 25978.0,
    "verify": 2656.0,
    "total": 28634.0,
    "image_pull": 0.0,
    "lost_tries": 0.0,
    "publish": 0.0,
    "queue_wait": 0.0,
    "task_fetch": 0.0
  },
  "source": {
    "name": "tb60-terminal-results.json",
    "sha256": "61f08d56b84c4e97e76530aca6d81074ebc5594b2c9bbc4da8f2c19f17d2b3f4"
  },
  "results": [
    {
      "order": 1,
      "task": "fix-git",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 18547,
      "requests": 19,
      "input_tokens": 174677,
      "cached_input_tokens": 116224,
      "output_tokens": 5379,
      "duration_total_s": 119.0,
      "factory_sha": "cc71172c3c687a2ac65469a03411ac4a2fdc66b5"
    },
    {
      "order": 2,
      "task": "prove-plus-comm",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 39513,
      "requests": 38,
      "input_tokens": 423890,
      "cached_input_tokens": 307712,
      "output_tokens": 9626,
      "duration_total_s": 165.0,
      "factory_sha": "cc71172c3c687a2ac65469a03411ac4a2fdc66b5"
    },
    {
      "order": 3,
      "task": "cobol-modernization",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 135047,
      "requests": 73,
      "input_tokens": 1504475,
      "cached_input_tokens": 1094144,
      "output_tokens": 22103,
      "duration_total_s": 193.0,
      "factory_sha": "cc71172c3c687a2ac65469a03411ac4a2fdc66b5"
    },
    {
      "order": 4,
      "task": "overfull-hbox",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 77101,
      "requests": 31,
      "input_tokens": 611054,
      "cached_input_tokens": 334592,
      "output_tokens": 20541,
      "duration_total_s": 320.0,
      "factory_sha": "cc71172c3c687a2ac65469a03411ac4a2fdc66b5"
    },
    {
      "order": 5,
      "task": "crack-7z-hash",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 35688,
      "requests": 31,
      "input_tokens": 325385,
      "cached_input_tokens": 194816,
      "output_tokens": 4195,
      "duration_total_s": 313.0,
      "factory_sha": "cc71172c3c687a2ac65469a03411ac4a2fdc66b5"
    },
    {
      "order": 6,
      "task": "mteb-leaderboard",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 6914,
      "requests": 9,
      "input_tokens": 60344,
      "cached_input_tokens": 41216,
      "output_tokens": 3543,
      "duration_total_s": 625.0,
      "factory_sha": "932970206d6baf8671889e3bc75499fa5dd1a833"
    },
    {
      "order": 7,
      "task": "raman-fitting",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 131994,
      "requests": 57,
      "input_tokens": 1304460,
      "cached_input_tokens": 889856,
      "output_tokens": 32799,
      "duration_total_s": 295.0,
      "factory_sha": "932970206d6baf8671889e3bc75499fa5dd1a833"
    },
    {
      "order": 8,
      "task": "constraints-scheduling",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 14123,
      "requests": 7,
      "input_tokens": 86258,
      "cached_input_tokens": 42496,
      "output_tokens": 9082,
      "duration_total_s": 122.0,
      "factory_sha": "932970206d6baf8671889e3bc75499fa5dd1a833"
    },
    {
      "order": 9,
      "task": "kv-store-grpc",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 28412,
      "requests": 27,
      "input_tokens": 242250,
      "cached_input_tokens": 139264,
      "output_tokens": 5391,
      "duration_total_s": 87.0,
      "factory_sha": "932970206d6baf8671889e3bc75499fa5dd1a833"
    },
    {
      "order": 10,
      "task": "mteb-retrieve",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 10390,
      "requests": 12,
      "input_tokens": 88305,
      "cached_input_tokens": 52992,
      "output_tokens": 2936,
      "duration_total_s": 695.0,
      "factory_sha": "932970206d6baf8671889e3bc75499fa5dd1a833"
    },
    {
      "order": 11,
      "task": "pytorch-model-recovery",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 36233,
      "requests": 17,
      "input_tokens": 211780,
      "cached_input_tokens": 60160,
      "output_tokens": 8508,
      "duration_total_s": 819.0,
      "factory_sha": "932970206d6baf8671889e3bc75499fa5dd1a833"
    },
    {
      "order": 12,
      "task": "break-filter-js-from-html",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 76184,
      "requests": 27,
      "input_tokens": 580058,
      "cached_input_tokens": 313856,
      "output_tokens": 25462,
      "duration_total_s": 544.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 13,
      "task": "hf-model-inference",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 20594,
      "requests": 22,
      "input_tokens": 202260,
      "cached_input_tokens": 136960,
      "output_tokens": 4983,
      "duration_total_s": 406.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 14,
      "task": "merge-diff-arc-agi-task",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 151224,
      "requests": 40,
      "input_tokens": 1256099,
      "cached_input_tokens": 661504,
      "output_tokens": 13614,
      "duration_total_s": 191.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 15,
      "task": "nginx-request-logging",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 39868,
      "requests": 29,
      "input_tokens": 387613,
      "cached_input_tokens": 250624,
      "output_tokens": 5829,
      "duration_total_s": 134.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 16,
      "task": "openssl-selfsigned-cert",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 19502,
      "requests": 22,
      "input_tokens": 161956,
      "cached_input_tokens": 91136,
      "output_tokens": 4089,
      "duration_total_s": 97.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 17,
      "task": "polyglot-c-py",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 51971,
      "requests": 14,
      "input_tokens": 317359,
      "cached_input_tokens": 129536,
      "output_tokens": 22719,
      "duration_total_s": 181.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 18,
      "task": "vulnerable-secret",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 26793,
      "requests": 18,
      "input_tokens": 211582,
      "cached_input_tokens": 111360,
      "output_tokens": 5548,
      "duration_total_s": 96.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 19,
      "task": "code-from-image",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 1165920,
      "requests": 110,
      "input_tokens": 9947232,
      "cached_input_tokens": 5362688,
      "output_tokens": 78821,
      "duration_total_s": 951.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 20,
      "task": "count-dataset-tokens",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 43637,
      "requests": 33,
      "input_tokens": 446264,
      "cached_input_tokens": 315392,
      "output_tokens": 11806,
      "duration_total_s": 158.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 21,
      "task": "custom-memory-heap-crash",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 102921,
      "requests": 43,
      "input_tokens": 964398,
      "cached_input_tokens": 619008,
      "output_tokens": 22005,
      "duration_total_s": 282.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 22,
      "task": "dna-insert",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 269815,
      "requests": 59,
      "input_tokens": 2625425,
      "cached_input_tokens": 1758208,
      "output_tokens": 63347,
      "duration_total_s": 433.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 23,
      "task": "extract-elf",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 247170,
      "requests": 26,
      "input_tokens": 1794679,
      "cached_input_tokens": 765696,
      "output_tokens": 25284,
      "duration_total_s": 265.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 24,
      "task": "financial-document-processor",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 95707,
      "requests": 38,
      "input_tokens": 861449,
      "cached_input_tokens": 509184,
      "output_tokens": 11574,
      "duration_total_s": 323.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 25,
      "task": "git-leak-recovery",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 10827,
      "requests": 16,
      "input_tokens": 113761,
      "cached_input_tokens": 82944,
      "output_tokens": 3272,
      "duration_total_s": 77.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 26,
      "task": "multi-source-data-merger",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 19166,
      "requests": 15,
      "input_tokens": 151946,
      "cached_input_tokens": 87040,
      "output_tokens": 6621,
      "duration_total_s": 129.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 27,
      "task": "pytorch-model-cli",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 42385,
      "requests": 30,
      "input_tokens": 370187,
      "cached_input_tokens": 222464,
      "output_tokens": 9548,
      "duration_total_s": 361.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 28,
      "task": "qemu-alpine-ssh",
      "verdict": "neutralized",
      "measurement": "null",
      "null_reason": "infra-verificateur-sentinelle",
      "credits": 158107,
      "requests": 58,
      "input_tokens": 1248663,
      "cached_input_tokens": 649728,
      "output_tokens": 29762,
      "duration_total_s": 918.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 29,
      "task": "qemu-startup",
      "verdict": "neutralized",
      "measurement": "null",
      "null_reason": "infra-verificateur-sentinelle",
      "credits": 519725,
      "requests": 79,
      "input_tokens": 4699745,
      "cached_input_tokens": 2701568,
      "output_tokens": 26723,
      "duration_total_s": 1001.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 30,
      "task": "reshard-c4-data",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 298299,
      "requests": 23,
      "input_tokens": 2121755,
      "cached_input_tokens": 844032,
      "output_tokens": 20588,
      "duration_total_s": 403.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 31,
      "task": "sanitize-git-repo",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 793435,
      "requests": 114,
      "input_tokens": 10467611,
      "cached_input_tokens": 8307200,
      "output_tokens": 67564,
      "duration_total_s": 621.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 32,
      "task": "sqlite-with-gcov",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 286330,
      "requests": 58,
      "input_tokens": 2629712,
      "cached_input_tokens": 1519616,
      "output_tokens": 6958,
      "duration_total_s": 364.0,
      "factory_sha": "285d856a35efe1ca3bd5f83cb441a3d93f82ecbe"
    },
    {
      "order": 33,
      "task": "tune-mjcf",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 167574,
      "requests": 51,
      "input_tokens": 1186562,
      "cached_input_tokens": 500480,
      "output_tokens": 24731,
      "duration_total_s": 942.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 34,
      "task": "large-scale-text-editing",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 29831,
      "requests": 17,
      "input_tokens": 234236,
      "cached_input_tokens": 129792,
      "output_tokens": 9170,
      "duration_total_s": 238.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 35,
      "task": "chess-best-move",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 233590,
      "requests": 38,
      "input_tokens": 1893021,
      "cached_input_tokens": 1070080,
      "output_tokens": 63985,
      "duration_total_s": 398.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 36,
      "task": "db-wal-recovery",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 87256,
      "requests": 28,
      "input_tokens": 669700,
      "cached_input_tokens": 314368,
      "output_tokens": 8455,
      "duration_total_s": 128.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 37,
      "task": "filter-js-from-html",
      "verdict": "neutralized",
      "measurement": "null",
      "null_reason": "infra-verificateur-sentinelle",
      "credits": 11040,
      "requests": 11,
      "input_tokens": 89932,
      "cached_input_tokens": 57344,
      "output_tokens": 5485,
      "duration_total_s": 379.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 38,
      "task": "regex-log",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 27765,
      "requests": 13,
      "input_tokens": 187895,
      "cached_input_tokens": 93440,
      "output_tokens": 12656,
      "duration_total_s": 126.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 39,
      "task": "build-cython-ext",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 300765,
      "requests": 102,
      "input_tokens": 3492710,
      "cached_input_tokens": 2539776,
      "output_tokens": 19455,
      "duration_total_s": 409.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 40,
      "task": "build-pov-ray",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 954374,
      "requests": 94,
      "input_tokens": 9346297,
      "cached_input_tokens": 5817344,
      "output_tokens": 33639,
      "duration_total_s": 669.0,
      "factory_sha": "a417a3b319bb17ce582bfc67a0cc6aca3743a55a"
    },
    {
      "order": 41,
      "task": "compile-compcert",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 468022,
      "requests": 64,
      "input_tokens": 3643643,
      "cached_input_tokens": 1672704,
      "output_tokens": 14306,
      "duration_total_s": 1606.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 42,
      "task": "gcode-to-text",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 932191,
      "requests": 95,
      "input_tokens": 9592106,
      "cached_input_tokens": 6411520,
      "output_tokens": 93082,
      "duration_total_s": 919.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 43,
      "task": "largest-eigenval",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 283315,
      "requests": 75,
      "input_tokens": 2784657,
      "cached_input_tokens": 1826304,
      "output_tokens": 44607,
      "duration_total_s": 829.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 44,
      "task": "mailman",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 166811,
      "requests": 62,
      "input_tokens": 1765822,
      "cached_input_tokens": 1226240,
      "output_tokens": 23488,
      "duration_total_s": 428.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 45,
      "task": "pypi-server",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 24898,
      "requests": 35,
      "input_tokens": 296101,
      "cached_input_tokens": 228352,
      "output_tokens": 5332,
      "duration_total_s": 246.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 46,
      "task": "query-optimize",
      "verdict": "neutralized",
      "measurement": "null",
      "null_reason": "infra-verificateur-sentinelle",
      "credits": 33850,
      "requests": 18,
      "input_tokens": 272749,
      "cached_input_tokens": 140032,
      "output_tokens": 4030,
      "duration_total_s": 1205.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 47,
      "task": "sqlite-db-truncate",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 50070,
      "requests": 14,
      "input_tokens": 259363,
      "cached_input_tokens": 119808,
      "output_tokens": 43088,
      "duration_total_s": 281.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 48,
      "task": "winning-avg-corewars",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 343810,
      "requests": 62,
      "input_tokens": 2827266,
      "cached_input_tokens": 1554432,
      "output_tokens": 65439,
      "duration_total_s": 754.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 49,
      "task": "log-summary-date-ranges",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 36288,
      "requests": 20,
      "input_tokens": 280565,
      "cached_input_tokens": 139008,
      "output_tokens": 5792,
      "duration_total_s": 199.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 50,
      "task": "build-pmars",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 156922,
      "requests": 44,
      "input_tokens": 1464468,
      "cached_input_tokens": 873472,
      "output_tokens": 8422,
      "duration_total_s": 478.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 51,
      "task": "distribution-search",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 57802,
      "requests": 25,
      "input_tokens": 446296,
      "cached_input_tokens": 238592,
      "output_tokens": 16396,
      "duration_total_s": 136.0,
      "factory_sha": "ec24ce5055f3d14c5191808fe7f41f7a7ecce90e"
    },
    {
      "order": 52,
      "task": "headless-terminal",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 37419,
      "requests": 26,
      "input_tokens": 303388,
      "cached_input_tokens": 174080,
      "output_tokens": 11219,
      "duration_total_s": 232.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 53,
      "task": "modernize-scientific-stack",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 8285,
      "requests": 11,
      "input_tokens": 82624,
      "cached_input_tokens": 58368,
      "output_tokens": 2681,
      "duration_total_s": 135.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 54,
      "task": "portfolio-optimization",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 84291,
      "requests": 34,
      "input_tokens": 664269,
      "cached_input_tokens": 357120,
      "output_tokens": 20867,
      "duration_total_s": 501.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 55,
      "task": "adaptive-rejection-sampler",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 144939,
      "requests": 22,
      "input_tokens": 957505,
      "cached_input_tokens": 382720,
      "output_tokens": 35745,
      "duration_total_s": 727.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 56,
      "task": "git-multibranch",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 67372,
      "requests": 46,
      "input_tokens": 722059,
      "cached_input_tokens": 515584,
      "output_tokens": 13156,
      "duration_total_s": 362.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 57,
      "task": "rstan-to-pystan",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 279557,
      "requests": 63,
      "input_tokens": 2284226,
      "cached_input_tokens": 1171968,
      "output_tokens": 23734,
      "duration_total_s": 1828.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 58,
      "task": "schemelike-metacircular-eval",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 548078,
      "requests": 97,
      "input_tokens": 6910941,
      "cached_input_tokens": 5444352,
      "output_tokens": 88911,
      "duration_total_s": 1133.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 59,
      "task": "caffe-cifar-10",
      "verdict": "fail",
      "measurement": "valid",
      "null_reason": null,
      "credits": 145177,
      "requests": 28,
      "input_tokens": 1232326,
      "cached_input_tokens": 652544,
      "output_tokens": 6853,
      "duration_total_s": 1305.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    },
    {
      "order": 60,
      "task": "configure-git-webserver",
      "verdict": "pass",
      "measurement": "valid",
      "null_reason": null,
      "credits": 280428,
      "requests": 77,
      "input_tokens": 3540033,
      "cached_input_tokens": 2725888,
      "output_tokens": 19556,
      "duration_total_s": 353.0,
      "factory_sha": "318a52fff0c8b66c5ca265f41776ae522734305a"
    }
  ],
  "official_score": {
    "passes": 39,
    "denominator": 89,
    "percent": 43.82022471910113,
    "executed": 60,
    "unexecuted": [
      "bn-fit-modify",
      "cancel-async-tasks",
      "circuit-fibsqrt",
      "dna-assembly",
      "extract-moves-from-video",
      "feal-differential-cryptanalysis",
      "feal-linear-cryptanalysis",
      "fix-code-vulnerability",
      "fix-ocaml-gc",
      "gpt2-codegolf",
      "install-windows-3.11",
      "llm-inference-batching-scheduler",
      "make-doom-for-mips",
      "make-mips-interpreter",
      "mcmc-sampling-stan",
      "model-extraction-relu-logits",
      "password-recovery",
      "path-tracing",
      "path-tracing-reverse",
      "polyglot-rust-c",
      "protein-assembly",
      "regex-chess",
      "sam-cell-seg",
      "sparql-university",
      "torch-pipeline-parallelism",
      "torch-tensor-parallelism",
      "train-fasttext",
      "video-processing",
      "write-compressor"
    ],
    "sampling_note": "29 tasks not executed by selection choice; assumed difficulty is not a measured result"
  }
}
