Reasoning on BRUMO25 (avg@k, Token reduction)
78.75Avg@k Score
Type IV (STOP)
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 78.75 | 277.5 | 78.98 | |
2026.04 | 76.25 | 284.8 | 78.43 | |
2026.04 | 75.83 | 394.9 | 70.1 | |
2026.04 | 75 | 1,320 | - | |
2026.04 | 74.58 | 280.2 | 78.78 | |
2026.04 | 70 | 183.6 | 68.11 | |
2026.04 | 69.17 | 187.6 | 67.41 | |
2026.04 | 68.02 | 575.6 | - | |
2026.04 | 67.92 | 179 | 68.9 | |
2026.04 | 66.25 | 298.8 | 48.09 | |
2026.04 | 56.67 | 190.2 | 71.03 | |
2026.04 | 52.92 | 194.5 | 70.38 | |
2026.04 | 51.25 | 312.1 | 52.46 | |
2026.04 | 50.99 | 656.6 | - | |
2026.04 | 50 | 199.3 | 69.64 | |
2026.04 | 33.75 | 204.4 | 73.61 | |
2026.04 | 31.67 | 325.6 | 57.96 | |
2026.04 | 31.67 | 209.7 | 72.93 | |
2026.04 | 30.99 | 774.6 | - | |
2026.04 | 29.58 | 212.8 | 72.53 |