Mathematical Problem Solving on AIME VeRA-H 2024-II
0.909Avg@5 (%)
GPT-5.1-high
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 0.909 | -3.4 | |
2026.01 | 0.84 | -7.4 | |
2026.01 | 0.823 | -6.3 | |
2026.01 | 0.82 | -10.9 | |
2026.01 | 0.811 | -13.1 | |
2026.01 | 0.811 | -8.9 | |
2026.01 | 0.766 | -10.6 | |
2026.01 | 0.766 | -16.3 | |
2026.01 | 0.746 | -1.1 | |
2026.01 | 0.72 | -18 | |
2026.01 | 0.703 | -18.3 | |
2026.01 | 0.643 | -18.6 | |
2026.01 | 0.591 | -20.9 | |
2026.01 | 0.406 | -30.9 | |
2026.01 | 0.343 | -18.6 | |
2026.01 | 0.151 | -70.6 |