Reasoning on AIME24, AIME25, HMMT25 Average
68.6Accuracy
SC@64
Updated 3mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 68.6 | 31.9 | 1,100.7 | |
2026.02 | 68.6 | 399.1 | 399.1 | |
2026.02 | 68.6 | 133.9 | 771.5 | |
2026.02 | 68.5 | 21.6 | 824.9 | |
2026.02 | 66.8 | 31.2 | 1,047.7 | |
2026.02 | 66.8 | 136.6 | 770.8 | |
2026.02 | 66.8 | 20.9 | 789 | |
2026.02 | 66.7 | 342.2 | 342.2 | |
2026.02 | 65.1 | 26.6 | 880.2 | |
2026.02 | 63.2 | 27.4 | 889.5 | |
2026.02 | 47 | 31.3 | 1,070.9 | |
2026.02 | 47 | 556.6 | 556.6 | |
2026.02 | 47 | 168.6 | 945.7 | |
2026.02 | 45.1 | 21.5 | 794.8 | |
2026.02 | 42 | 26.9 | 888.8 | |
2026.02 | 23.3 | 20.3 | 735.3 | |
2026.02 | 22.8 | 31.6 | 945.7 | |
2026.02 | 22.8 | 680 | 680 | |
2026.02 | 22.8 | 181.4 | 926.5 | |
2026.02 | 20.7 | 26.8 | 816.1 |