SUBMISSION / VERIFIED
Final norm gain × 1.25 (temperature-0.8 equivalent)
Verified
Starting evaluation…
VALIDATION41.45%Equal-weight average of public benchmarks-0.38 points vs. original
PRIVATE TEST19.00%Determines leaderboard rank0.40 points vs. original
Validation breakdown
| Public benchmark | Score |
|---|---|
| bbh | 35.19% |
| mbpp | 18.75% |
| mmlu | 47.37% |
| piqa | 71.88% |
| boolq | 64.06% |
| gsm8k | 59.38% |
| ifeval | 50.00% |
| math500 | 45.31% |
| arc_easy | 65.63% |
| mmlu_pro | 32.86% |
| hellaswag | 45.31% |
| humaneval | 25.00% |
| openbookqa | 29.69% |
| winogrande | 56.25% |
| arc_challenge | 28.13% |
| commonsense_qa | 54.69% |
| 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 4, 2026 · 20:17 UTC | 23.33% | 22.22% |
| Nov 4, 2026 · 23:48 UTC | 41.45% | 19.00% |
A dash means no result yet. Private test questions, answers, and individual results are never included here.