Long-horizon Mathematical Reasoning on MATH (Result and Process Metrics)
89.2Result Accuracy
Qwen-2-72B-Instruct
Updated 5d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 89.2 | - | |
2026.05 | 82.7 | - | |
2026.05 | 80.5 | - | |
2026.05 | 80 | - | |
2026.05 | 79.4 | - | |
2026.05 | 78.2 | - | |
2026.05 | 77.6 | - | |
2026.04 | 77.46 | 76.89 | |
2026.04 | 75.38 | 74.62 | |
2026.04 | 74.43 | 71.97 | |
2026.04 | 74.24 | 73.11 | |
2026.04 | 67.61 | 65.72 | |
2026.05 | 65.4 | - | |
2026.04 | 56.25 | 56.06 | |
2026.04 | 54.55 | 52.08 | |
2026.04 | 53.98 | 52.65 | |
2026.04 | 53.6 | 49.62 | |
2026.04 | 53.6 | 52.27 | |
2026.04 | 52.65 | 50.57 | |
2026.04 | 52.08 | 50.57 | |
2026.04 | 49.81 | 47.35 | |
2026.04 | 47.73 | 43.94 | |
2026.05 | 45.5 | - |