Fresh 86-task run after engine parallel-tool and harness command-timeout fixes. Scores below include terminal timeout deductions. Engine health, response ownership and bundle integrity are checked separately by the final audit. The saved prime-test-suite-fair submission was regraded from an evaluator-timeout zero to 5.67/6 using the same cases and scoring. The raw ledger and original archive are preserved; its task ZIP includes the regrading logs. Recorded run time excludes the additional offline grading CPU time. Prior R1 records are preserved.
| Task | Status | Raw grade | Timeout deduction | Effective grade | Seconds / budget | API errors | Checks |
|---|---|---|---|---|---|---|---|
| api-contract-drift | completed | 5.0/5.0 | 0.0 | 5.0/5.0 | 37.4 / 900 | 0 | passed |
| comfyui-run-workflow | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 86.3 / 900 | 0 | passed |
| comfyui-sd | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 184.9 / 900 | 0 | passed |
| comfyui-sd-lora | completed | 3.0/10.0 | 0.0 | 3.0/10.0 | 405.8 / 900 | 0 | passed |
| comfyui-sd-sweep | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 160.0 / 900 | 0 | passed |
| comfyui-sd-twostage | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 229.6 / 900 | 0 | passed |
| comfyui-sweep | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 120.8 / 900 | 0 | passed |
| conv-dim-build | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 23.3 / 900 | 0 | passed |
| conv-dim-fix | completed | 3.0/3.0 | 0.0 | 3.0/3.0 | 20.1 / 900 | 0 | passed |
| conv-dim-stride | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 27.9 / 900 | 0 | passed |
| countdown-game | completed | 3.0/3.0 | 0.0 | 3.0/3.0 | 327.3 / 900 | 0 | passed |
| countdown-hard | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 9.3 / 900 | 0 | passed |
| crypto-encrypt-blob | completed | 7.0/7.0 | 0.0 | 7.0/7.0 | 32.7 / 900 | 0 | passed |
| crypto-encrypt-blob-no-append | completed | 11.0/11.0 | 0.0 | 11.0/11.0 | 56.2 / 900 | 0 | passed |
| crypto-password-store | completed | 6.0/6.0 | 0.0 | 6.0/6.0 | 17.4 / 900 | 0 | passed |
| file-ring | completed | 3.0/3.0 | 0.0 | 3.0/3.0 | 8.2 / 900 | 0 | passed |
| file-ring-checksum | completed | 9.0/9.0 | 0.0 | 9.0/9.0 | 15.2 / 900 | 0 | passed |
| file-ring-creative | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 10.8 / 900 | 0 | passed |
| file-ring-creative-actcue | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 6.7 / 900 | 0 | passed |
| file-ring-creative-noexample | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 7.8 / 900 | 0 | passed |
| file-ring-creative-v2 | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 8.1 / 900 | 0 | passed |
| file-ring-impossible | completed | 3.0/3.0 | 0.0 | 3.0/3.0 | 9.6 / 900 | 0 | passed |
| file-ring-resolve | completed | 6.0/6.0 | 0.0 | 6.0/6.0 | 11.5 / 900 | 0 | passed |
| file-ring-traverse | completed | 6.0/6.0 | 0.0 | 6.0/6.0 | 16.7 / 900 | 0 | passed |
| fmtspec-mini | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 219.5 / 900 | 0 | passed |
| framed-kv | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 84.1 / 900 | 0 | passed |
| jsoncanon | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 134.7 / 900 | 0 | passed |
| kv-stress-distractor-prime | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 22.5 / 900 | 0 | passed |
| kv-stress-longctx-logic | completed | 2.0/2.0 | 0.0 | 2.0/2.0 | 52.7 / 900 | 0 | passed |
| kv-stress-longctx-pricing | completed | 8.0/8.0 | 0.0 | 8.0/8.0 | 48.0 / 900 | 0 | passed |
| kv-stress-resume-calc | completed | 5.0/5.0 | 0.0 | 5.0/5.0 | 29.0 / 900 | 0 | passed |
| memcached-bisect-buried | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 131.5 / 900 | 0 | passed |
| memcached-bisect-deep | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 275.1 / 900 | 0 | passed |
| memcached-bisect-easy | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 103.2 / 900 | 0 | passed |
| memcached-op-isprime | completed | 2.0/10.0 | 0.0 | 2.0/10.0 | 15.7 / 900 | 0 | passed |
| memcached-op-mult | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 84.5 / 900 | 0 | passed |
| memcached-op-sayhi | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 68.3 / 900 | 0 | passed |
| minesweeper-server | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 151.4 / 900 | 0 | passed |
| minesweeper3d-server | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 122.9 / 900 | 0 | passed |
| no-op-trap | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 9.1 / 900 | 0 | passed |
| numba-stencil-modes | completed | 0.0/10.0 | 0.0 | 0.0/10.0 | 378.4 / 1800 | 0 | passed |
| patmatch-basic | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 96.1 / 900 | 0 | passed |
| patmatch-classes | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 370.9 / 900 | 0 | passed |
| patmatch-rules | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 395.1 / 1800 | 0 | passed |
| prime-add-test | completed | 2.0/2.0 | 0.0 | 2.0/2.0 | 14.5 / 900 | 0 | passed |
| prime-build | completed | 8.0/8.0 | 0.0 | 8.0/8.0 | 74.1 / 900 | 0 | passed |
| prime-factor | completed | 8.0/8.0 | 0.0 | 8.0/8.0 | 44.3 / 900 | 0 | passed |
| prime-factor-cache | timeout | 10.0/10.0 | 5.0 | 5.0/10.0 | 902.9 / 900 | 0 | passed |
| prime-factor-fast | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 115.7 / 900 | 0 | passed |
| prime-frontend | completed | 6.0/10.0 | 0.0 | 6.0/10.0 | 49.9 / 900 | 0 | passed |
| prime-test-suite | completed | 7.0/7.0 | 0.0 | 7.0/7.0 | 31.9 / 900 | 0 | passed |
| prime-test-suite-fair | completed | 0.0/1.0 | 0.0 | 5.67/6.0 | 337.4 / 900 | 0 | passed |
| prime-test-suite-minimal | completed | 6.0/6.0 | 0.0 | 6.0/6.0 | 104.3 / 900 | 0 | passed |
| prime-test-suite-old | completed | 6.0/6.0 | 0.0 | 6.0/6.0 | 110.3 / 900 | 0 | passed |
| prime-test-suite-opus | completed | 6.0/6.0 | 0.0 | 6.0/6.0 | 84.5 / 900 | 0 | passed |
| psim-arc | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 133.7 / 900 | 0 | passed |
| psim-basic | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 120.6 / 900 | 0 | passed |
| psim-blackbox | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 1034.3 / 1800 | 0 | passed |
| psim-blackbox-sealed | timeout | 9.333/10.0 | 5.0 | 4.333/10.0 | 1802.3 / 1800 | 0 | passed |
| psim-blackbox-xl | completed | 0.0/10.0 | 0.0 | 0.0/10.0 | 24.9 / 1800 | 0 | passed |
| psim-collide | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 127.7 / 900 | 0 | passed |
| psim-fixbugs | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 536.6 / 900 | 0 | passed |
| psim-nbody | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 117.7 / 1800 | 0 | passed |
| psim-nbody-terse | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 179.0 / 900 | 0 | passed |
| py2c-calc | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 488.6 / 1800 | 0 | passed |
| py2c-calcvars | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 445.2 / 1800 | 0 | passed |
| py2c-minivm | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 269.4 / 900 | 0 | passed |
| refactor-rename | completed | 6.0/6.0 | 0.0 | 6.0/6.0 | 21.2 / 900 | 0 | passed |
| regex-golf | completed | 20.0/20.0 | 0.0 | 20.0/20.0 | 15.9 / 900 | 0 | passed |
| rex-blackbox-sealed | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 1660.2 / 1800 | 0 | passed |
| sql-join-order | completed | 5.0/5.0 | 0.0 | 5.0/5.0 | 17.6 / 900 | 0 | passed |
| statefile-migrate | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 62.4 / 900 | 0 | passed |
| strided-conv-inverse | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 18.0 / 900 | 0 | passed |
| swebench-django-acreate | completed | 7.33/10.0 | 0.0 | 7.33/10.0 | 168.6 / 900 | 0 | passed |
| swebench-django-escapeseq | completed | 6.0/10.0 | 0.0 | 6.0/10.0 | 167.5 / 900 | 0 | passed |
| swebench-django-serialm2m | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 198.2 / 1800 | 0 | passed |
| swebench-pytest-caplog | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 226.7 / 900 | 0 | passed |
| swebench-pytest-mro | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 388.6 / 900 | 0 | passed |
| swebench-pytest-skippdb | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 55.9 / 900 | 0 | passed |
| tcp-reno | completed | 6.0/10.0 | 0.0 | 6.0/10.0 | 179.9 / 1800 | 0 | passed |
| transformer-shape | completed | 5.0/5.0 | 0.0 | 5.0/5.0 | 22.7 / 900 | 0 | passed |
| udiff-apply | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 218.1 / 900 | 0 | passed |
| verify-before-claim | completed | 4.0/4.0 | 0.0 | 4.0/4.0 | 18.1 / 900 | 0 | passed |
| vm-blackbox-sealed | completed | 10.0/10.0 | 0.0 | 10.0/10.0 | 1595.5 / 1800 | 0 | passed |
| write-hello | completed | 1.0/1.0 | 0.0 | 1.0/1.0 | 6.9 / 900 | 0 | passed |
| write-hello-word | completed | 1.0/1.0 | 0.0 | 1.0/1.0 | 7.7 / 900 | 0 | passed |