Mathematical Reasoning on OlympiadBench (Acc, AUROC, ECE)
37.6Accuracy
RLVR
Updated 23d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.07 | 37.6 | 51.4 | 61.6 | |
2026.07 | 37.5 | 78.3 | 19.1 | |
2026.07 | 35.9 | 74.5 | 26.3 | |
2026.07 | 35.4 | 80.5 | 14.7 | |
2026.07 | 28.3 | 79.9 | 7.1 | |
2026.07 | 26.6 | 78.3 | 9 | |
2026.07 | 20.3 | 59.4 | 70.9 | |
2026.07 | 17 | 59.3 | 75.4 | |
2026.07 | 16.2 | 65.6 | 27.8 | |
2026.07 | 15.8 | 64.1 | 28.9 | |
2026.07 | 12.8 | 65.7 | 7.7 | |
2026.07 | 10.3 | 73.2 | 14.1 | |
2026.07 | 8.6 | 63.1 | 12 | |
2026.07 | 8.3 | 55.9 | 37.9 | |
2026.07 | 5.2 | 58.3 | 17 | |
2026.07 | 3.3 | 65.4 | 8.3 |