Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion backend/benchmarks.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,4 +19,12 @@ def load_benchmark_reports(root: Path) -> tuple[BenchmarkReport, ...]:
).benchmark_version
== BENCHMARK_VERSION
]
return tuple(sorted(reports, key=lambda report: report.completed_at, reverse=True))
return tuple(
sorted(
reports,
key=lambda report: (
not report.model.startswith("digital-forge:"),
-report.completed_at.timestamp(),
),
)
)
294 changes: 294 additions & 0 deletions benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/report.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,294 @@
{
"schema_version": "1.1.0",
"benchmark_version": "1.1.0",
"evaluator_sha256": "cc95a687dc7e8200dde2700ad87d744b3f0dbe004bd6d9285c17bb3beefc3f2b",
"run_id": "3da7bfb192c84a47aedc04a1d20be0f7",
"model": "gpt-4o-mini",
"sandbox_backend": "docker",
"started_at": "2026-07-16T22:08:53.162884Z",
"completed_at": "2026-07-16T22:10:00.087609Z",
"tasks_passed": 14,
"tasks_total": 20,
"results": [
{
"task_id": "forge_easy_01",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": false,
"tests_passed": 3,
"tests_total": 4,
"duration_seconds": 3.2775099579885136,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_01.py",
"response_id": "resp_01dee794ab8dd589016a59567677fc819490fec143ddc4fe2d",
"input_tokens": 136,
"output_tokens": 147,
"error": "hidden case failed during hidden case 3"
},
{
"task_id": "forge_easy_02",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.302995167003246,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_02.py",
"response_id": "resp_052df5c00c8d8c84016a59567d93e88195bbd63bc9f7cc11ba",
"input_tokens": 187,
"output_tokens": 124,
"error": null
},
{
"task_id": "forge_easy_03",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.35199062500032596,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_03.py",
"response_id": "resp_0defad304ea562aa016a595681aba08194b077d0ee4c92f9c1",
"input_tokens": 160,
"output_tokens": 134,
"error": null
},
{
"task_id": "forge_easy_04",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.35644937501638196,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_04.py",
"response_id": "resp_0a56148735cc227b016a595684f57c819485b65f5f0d5a1aad",
"input_tokens": 162,
"output_tokens": 127,
"error": null
},
{
"task_id": "forge_easy_05",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.3724028750148136,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_05.py",
"response_id": "resp_015ec888d0cb8a23016a595687719c81959acc5b247b07fa0e",
"input_tokens": 175,
"output_tokens": 173,
"error": null
},
{
"task_id": "forge_easy_06",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": false,
"tests_passed": 0,
"tests_total": 4,
"duration_seconds": 0.433890040992992,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_06.py",
"response_id": "resp_0a91472275072263016a59568a09f08196b143909a3b41ff9f",
"input_tokens": 127,
"output_tokens": 101,
"error": "hidden case failed during hidden case 0"
},
{
"task_id": "forge_easy_07",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": false,
"tests_passed": 2,
"tests_total": 4,
"duration_seconds": 0.2925869589962531,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_07.py",
"response_id": "resp_05d16c4d0b7a3a94016a59568cd6b48197bcd39397d63aba9d",
"input_tokens": 156,
"output_tokens": 119,
"error": "hidden case failed during hidden case 2"
},
{
"task_id": "forge_easy_08",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.22496262498316355,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_08.py",
"response_id": "resp_0e79bff60b773e73016a59568fae2c8195aa258139b5c5c6d4",
"input_tokens": 157,
"output_tokens": 98,
"error": null
},
{
"task_id": "forge_easy_09",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.3621526249917224,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_09.py",
"response_id": "resp_07e015a27f18a9dd016a595692279481948eeb266697f83464",
"input_tokens": 147,
"output_tokens": 135,
"error": null
},
{
"task_id": "forge_easy_10",
"task_version": "1.1.0",
"difficulty": "easy",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.33703416597563773,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_easy_10.py",
"response_id": "resp_0c376e4bf2a266e5016a5956946ebc8195b282891baa080b57",
"input_tokens": 152,
"output_tokens": 149,
"error": null
},
{
"task_id": "forge_medium_01",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.30225487498682924,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_01.py",
"response_id": "resp_05c2c6e546601458016a595696a27c8194bf7527ac420d907a",
"input_tokens": 194,
"output_tokens": 237,
"error": null
},
{
"task_id": "forge_medium_02",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": false,
"tests_passed": 1,
"tests_total": 4,
"duration_seconds": 0.32492045799153857,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_02.py",
"response_id": "resp_0ea50ab90a61de9e016a595699ea10819583c0d18d94218f58",
"input_tokens": 168,
"output_tokens": 285,
"error": "hidden case failed during hidden case 1"
},
{
"task_id": "forge_medium_03",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.35062162499525584,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_03.py",
"response_id": "resp_0dcadecaf3981c52016a59569e211c819487912a4b000acebd",
"input_tokens": 158,
"output_tokens": 201,
"error": null
},
{
"task_id": "forge_medium_04",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": false,
"tests_passed": 0,
"tests_total": 4,
"duration_seconds": 0.307560207991628,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_04.py",
"response_id": "resp_07eb725e43f1972a016a5956a156a08193879597b2392dcd79",
"input_tokens": 168,
"output_tokens": 177,
"error": "hidden case failed during hidden case 0"
},
{
"task_id": "forge_medium_05",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.3377802910108585,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_05.py",
"response_id": "resp_0770e6c978b93d2d016a5956a3e1ac8197bfedcf67e31cc539",
"input_tokens": 130,
"output_tokens": 182,
"error": null
},
{
"task_id": "forge_medium_06",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": false,
"tests_passed": 1,
"tests_total": 4,
"duration_seconds": 0.2906482909747865,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_06.py",
"response_id": "resp_0b130ad2167f830a016a5956a6f664819782a3e77d1a31c7ca",
"input_tokens": 143,
"output_tokens": 258,
"error": "hidden case failed during hidden case 1"
},
{
"task_id": "forge_medium_07",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.23271266699885018,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_07.py",
"response_id": "resp_0c064b2e1547ac7a016a5956ab01808193a5442698153618ca",
"input_tokens": 160,
"output_tokens": 198,
"error": null
},
{
"task_id": "forge_medium_08",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.2234365420008544,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_08.py",
"response_id": "resp_09999fdc45ea51cd016a5956ade4bc8195a52573be4ef8457b",
"input_tokens": 161,
"output_tokens": 138,
"error": null
},
{
"task_id": "forge_medium_09",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.88722304199473,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_09.py",
"response_id": "resp_0c12e4c5b4b7431d016a5956b05e0c8190a7b3f26ba41a42c7",
"input_tokens": 143,
"output_tokens": 190,
"error": null
},
{
"task_id": "forge_medium_10",
"task_version": "1.1.0",
"difficulty": "medium",
"passed": true,
"tests_passed": 4,
"tests_total": 4,
"duration_seconds": 0.7286064169893507,
"candidate_path": "benchmark-results/3da7bfb192c84a47aedc04a1d20be0f7/candidates/forge_medium_10.py",
"response_id": "resp_05b994bfc13f379a016a5956b4afe88190ac4d77e1072b516e",
"input_tokens": 182,
"output_tokens": 161,
"error": null
}
]
}
Loading
Loading