← BBW graph · Download audit JSON
Provisional engine result. The known parallel tool-call defect makes this unsuitable as a certified clean benchmark. The original ledger and archives are retained. Corrected grading logs were added to the Minesweeper task bundle.
All six timeouts: raw 10/10, minus five points, recorded 5/10. Minesweeper was regraded from its saved submission after correcting the evaluator import: 0 to 10/10. One client timeout was recovered by Pi; its attempt did not reach the serving proxy. The bundled Pi launcher bypassed Regina’s bash timeout patch: rows record 120 seconds, but no default cap was active. The 900/1800-second task limits and their five-point deductions were verified.
| Task | Status | Raw grade | Timeout deduction | Corrected score | Seconds / budget | API errors | Checks |
|---|---|---|---|---|---|---|---|
| api-contract-drift | completed | 5.0/5.0 | 0.0 | 5.0 | 43.7 / 900 | 0 | passed |
| comfyui-run-workflow | completed | 10.0/10.0 | 0.0 | 10.0 | 47.5 / 900 | 0 | passed |
| comfyui-sd | completed | 10.0/10.0 | 0.0 | 10.0 | 66.8 / 900 | 0 | passed |
| comfyui-sd-lora | completed | 3.0/10.0 | 0.0 | 3.0 | 399.4 / 900 | 0 | passed |
| comfyui-sd-sweep | completed | 10.0/10.0 | 0.0 | 10.0 | 156.2 / 900 | 0 | passed |
| comfyui-sd-twostage | completed | 10.0/10.0 | 0.0 | 10.0 | 452.1 / 900 | 0 | passed |
| comfyui-sweep | completed | 10.0/10.0 | 0.0 | 10.0 | 132.0 / 900 | 0 | passed |
| conv-dim-build | completed | 1.0/4.0 | 0.0 | 1.0 | 34.5 / 900 | 0 | passed |
| conv-dim-fix | completed | 3.0/3.0 | 0.0 | 3.0 | 30.2 / 900 | 0 | passed |
| conv-dim-stride | completed | 4.0/4.0 | 0.0 | 4.0 | 33.1 / 900 | 0 | passed |
| countdown-game | completed | 3.0/3.0 | 0.0 | 3.0 | 10.6 / 900 | 0 | passed |
| countdown-hard | completed | 4.0/4.0 | 0.0 | 4.0 | 9.0 / 900 | 0 | passed |
| crypto-encrypt-blob | completed | 7.0/7.0 | 0.0 | 7.0 | 19.6 / 900 | 0 | passed |
| crypto-encrypt-blob-no-append | completed | 11.0/11.0 | 0.0 | 11.0 | 43.3 / 900 | 0 | passed |
| crypto-password-store | completed | 6.0/6.0 | 0.0 | 6.0 | 56.5 / 900 | 0 | passed |
| file-ring | completed | 3.0/3.0 | 0.0 | 3.0 | 12.9 / 900 | 0 | passed |
| file-ring-checksum | completed | 9.0/9.0 | 0.0 | 9.0 | 28.6 / 900 | 0 | passed |
| file-ring-creative | completed | 4.0/4.0 | 0.0 | 4.0 | 11.6 / 900 | 0 | passed |
| file-ring-creative-actcue | completed | 4.0/4.0 | 0.0 | 4.0 | 9.9 / 900 | 0 | passed |
| file-ring-creative-noexample | completed | 4.0/4.0 | 0.0 | 4.0 | 9.2 / 900 | 0 | passed |
| file-ring-creative-v2 | completed | 4.0/4.0 | 0.0 | 4.0 | 6.3 / 900 | 0 | passed |
| file-ring-impossible | completed | 3.0/3.0 | 0.0 | 3.0 | 20.9 / 900 | 0 | passed |
| file-ring-resolve | completed | 6.0/6.0 | 0.0 | 6.0 | 24.0 / 900 | 0 | passed |
| file-ring-traverse | completed | 6.0/6.0 | 0.0 | 6.0 | 24.3 / 900 | 0 | passed |
| fmtspec-mini | completed | 10.0/10.0 | 0.0 | 10.0 | 167.3 / 900 | 0 | passed |
| framed-kv | completed | 10.0/10.0 | 0.0 | 10.0 | 327.5 / 900 | 0 | passed |
| jsoncanon | completed | 10.0/10.0 | 0.0 | 10.0 | 136.2 / 900 | 0 | passed |
| kv-stress-distractor-prime | completed | 4.0/4.0 | 0.0 | 4.0 | 19.6 / 900 | 0 | passed |
| kv-stress-longctx-logic | completed | 2.0/2.0 | 0.0 | 2.0 | 51.7 / 900 | 0 | passed |
| kv-stress-longctx-pricing | completed | 8.0/8.0 | 0.0 | 8.0 | 46.2 / 900 | 0 | passed |
| kv-stress-resume-calc | completed | 5.0/5.0 | 0.0 | 5.0 | 22.9 / 900 | 0 | passed |
| memcached-bisect-buried | completed | 10.0/10.0 | 0.0 | 10.0 | 57.0 / 900 | 0 | passed |
| memcached-bisect-deep | completed | 10.0/10.0 | 0.0 | 10.0 | 129.3 / 900 | 0 | passed |
| memcached-bisect-easy | completed | 10.0/10.0 | 0.0 | 10.0 | 52.3 / 900 | 0 | passed |
| memcached-op-isprime | completed | 10.0/10.0 | 0.0 | 10.0 | 337.4 / 900 | 0 | passed |
| memcached-op-mult | completed | 2.0/10.0 | 0.0 | 2.0 | 19.2 / 900 | 0 | passed |
| memcached-op-sayhi | completed | 10.0/10.0 | 0.0 | 10.0 | 39.6 / 900 | 0 | passed |
| minesweeper-server | completed | 0.0/10.0 | 0.0 | 10.0 | 187.7 / 900 | 0 | passed |
| minesweeper3d-server | completed | 10.0/10.0 | 0.0 | 10.0 | 181.2 / 900 | 0 | passed |
| no-op-trap | completed | 4.0/4.0 | 0.0 | 4.0 | 9.3 / 900 | 0 | passed |
| numba-stencil-modes | completed | 10.0/10.0 | 0.0 | 10.0 | 1364.5 / 1800 | 0 | passed |
| patmatch-basic | completed | 10.0/10.0 | 0.0 | 10.0 | 59.4 / 900 | 0 | passed |
| patmatch-classes | timeout | 10.0/10.0 | 5.0 | 5.0 | 901.7 / 900 | 0 | passed |
| patmatch-rules | completed | 10.0/10.0 | 0.0 | 10.0 | 189.1 / 1800 | 0 | passed |
| prime-add-test | completed | 2.0/2.0 | 0.0 | 2.0 | 12.2 / 900 | 0 | passed |
| prime-build | completed | 8.0/8.0 | 0.0 | 8.0 | 33.7 / 900 | 0 | passed |
| prime-factor | completed | 8.0/8.0 | 0.0 | 8.0 | 34.4 / 900 | 0 | passed |
| prime-factor-cache | timeout | 10.0/10.0 | 5.0 | 5.0 | 903.0 / 900 | 0 | passed |
| prime-factor-fast | completed | 10.0/10.0 | 0.0 | 10.0 | 54.8 / 900 | 0 | passed |
| prime-frontend | completed | 10.0/10.0 | 0.0 | 10.0 | 41.8 / 900 | 0 | passed |
| prime-test-suite | completed | 7.0/7.0 | 0.0 | 7.0 | 27.7 / 900 | 0 | passed |
| prime-test-suite-fair | completed | 6.0/6.0 | 0.0 | 6.0 | 28.3 / 900 | 0 | passed |
| prime-test-suite-minimal | completed | 6.0/6.0 | 0.0 | 6.0 | 139.8 / 900 | 0 | passed |
| prime-test-suite-old | completed | 6.0/6.0 | 0.0 | 6.0 | 130.7 / 900 | 0 | passed |
| prime-test-suite-opus | completed | 6.0/6.0 | 0.0 | 6.0 | 106.0 / 900 | 0 | passed |
| psim-arc | completed | 10.0/10.0 | 0.0 | 10.0 | 116.5 / 900 | 0 | passed |
| psim-basic | completed | 10.0/10.0 | 0.0 | 10.0 | 77.8 / 900 | 0 | passed |
| psim-blackbox | completed | 10.0/10.0 | 0.0 | 10.0 | 619.5 / 1800 | 0 | passed |
| psim-blackbox-sealed | completed | 8.667/10.0 | 0.0 | 8.667 | 1647.9 / 1800 | 0 | passed |
| psim-blackbox-xl | completed | 10.0/10.0 | 0.0 | 10.0 | 1637.2 / 1800 | 0 | passed |
| psim-collide | timeout | 10.0/10.0 | 5.0 | 5.0 | 902.1 / 900 | 0 | passed |
| psim-fixbugs | completed | 10.0/10.0 | 0.0 | 10.0 | 211.3 / 900 | 0 | passed |
| psim-nbody | completed | 10.0/10.0 | 0.0 | 10.0 | 91.6 / 1800 | 0 | passed |
| psim-nbody-terse | timeout | 10.0/10.0 | 5.0 | 5.0 | 901.9 / 900 | 0 | passed |
| py2c-calc | completed | 10.0/10.0 | 0.0 | 10.0 | 1671.1 / 1800 | 0 | passed |
| py2c-calcvars | timeout | 10.0/10.0 | 5.0 | 5.0 | 1801.7 / 1800 | 0 | passed |
| py2c-minivm | completed | 10.0/10.0 | 0.0 | 10.0 | 568.7 / 900 | 0 | passed |
| refactor-rename | completed | 6.0/6.0 | 0.0 | 6.0 | 29.2 / 900 | 0 | passed |
| regex-golf | completed | 20.0/20.0 | 0.0 | 20.0 | 18.2 / 900 | 0 | passed |
| rex-blackbox-sealed | timeout | 10.0/10.0 | 5.0 | 5.0 | 1802.1 / 1800 | 0 | passed |
| sql-join-order | completed | 5.0/5.0 | 0.0 | 5.0 | 26.7 / 900 | 0 | passed |
| statefile-migrate | completed | 10.0/10.0 | 0.0 | 10.0 | 61.0 / 900 | 0 | passed |
| strided-conv-inverse | completed | 4.0/4.0 | 0.0 | 4.0 | 18.1 / 900 | 0 | passed |
| swebench-django-acreate | completed | 4.67/10.0 | 0.0 | 4.67 | 120.7 / 900 | 1 | passed |
| swebench-django-escapeseq | completed | 6.0/10.0 | 0.0 | 6.0 | 115.1 / 900 | 0 | passed |
| swebench-django-serialm2m | completed | 8.440000000000001/10.0 | 0.0 | 8.440000000000001 | 887.6 / 1800 | 0 | passed |
| swebench-pytest-caplog | completed | 10.0/10.0 | 0.0 | 10.0 | 221.9 / 900 | 0 | passed |
| swebench-pytest-mro | completed | 2.0/10.0 | 0.0 | 2.0 | 46.2 / 900 | 0 | passed |
| swebench-pytest-skippdb | completed | 3.0/10.0 | 0.0 | 3.0 | 16.1 / 900 | 0 | passed |
| tcp-reno | completed | 2.0/10.0 | 0.0 | 2.0 | 181.7 / 1800 | 0 | passed |
| transformer-shape | completed | 5.0/5.0 | 0.0 | 5.0 | 19.3 / 900 | 0 | passed |
| udiff-apply | completed | 10.0/10.0 | 0.0 | 10.0 | 180.1 / 900 | 0 | passed |
| verify-before-claim | completed | 4.0/4.0 | 0.0 | 4.0 | 11.5 / 900 | 0 | passed |
| vm-blackbox-sealed | completed | 10.0/10.0 | 0.0 | 10.0 | 1689.5 / 1800 | 0 | passed |
| write-hello | completed | 1.0/1.0 | 0.0 | 1.0 | 6.2 / 900 | 0 | passed |
| write-hello-word | completed | 1.0/1.0 | 0.0 | 1.0 | 8.6 / 900 | 0 | passed |