SUBMISSION / VERIFIED
Repetition-direction removal × 1.5 (scale 9 on the published edit)
Verified
Starting evaluation…
VALIDATION39.59%Equal-weight average of public benchmarks-2.24 points vs. original
PRIVATE TEST13.80%Determines leaderboard rank-4.80 points vs. original
Validation breakdown
| Public benchmark | Score |
|---|---|
| bbh | 16.67% |
| mbpp | 12.50% |
| mmlu | 43.86% |
| piqa | 68.75% |
| boolq | 64.06% |
| gsm8k | 46.88% |
| ifeval | 59.38% |
| math500 | 37.50% |
| arc_easy | 67.19% |
| mmlu_pro | 22.86% |
| hellaswag | 46.88% |
| humaneval | 34.38% |
| openbookqa | 32.81% |
| winogrande | 56.25% |
| arc_challenge | 29.69% |
| commonsense_qa | 56.25% |
| bfcl_multi_turn | 0.00% |
| bfcl_single_turn | 16.67% |
Evaluation history
Earlier scores remain visible when the test set changes. Compare scores only within the same evaluation version.
| Completed | Validation | Private test |
|---|---|---|
| Nov 5, 2026 · 00:36 UTC | 39.59% | 13.80% |
A dash means no result yet. Private test questions, answers, and individual results are never included here.