Mathematical Reasoning on MATH, GSM, and AIME Suite
80.1MATH Score
CARE-RL
Updated 1d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 80.1 | 94.3 | 14.2 | 62.9 | |
2026.05 | 79.7 | 93.2 | 9.2 | 60.7 | |
2026.05 | 79.4 | 93.9 | 11.7 | 61.7 | |
2026.05 | 79 | 93.6 | 14.2 | 62.3 | |
2026.05 | 78.8 | 93.7 | 13.3 | 61.9 | |
2026.05 | 78.6 | 92.7 | 7.5 | 59.6 | |
2026.05 | 78.2 | 92.2 | 8.3 | 59.6 | |
2026.05 | 78.1 | 93 | 9.2 | 60.1 | |
2026.05 | 77.6 | 92.6 | 10.8 | 60.3 | |
2026.05 | 77.4 | 92 | 7.5 | 59 | |
2026.05 | 76.2 | 91.4 | 5.8 | 57.8 | |
2026.05 | 75.9 | 90.8 | 5.8 | 57.5 | |
2026.05 | 68.4 | 87.8 | 4.2 | 53.5 | |
2026.05 | 60.9 | 84.7 | 4.2 | 49.9 |