Long-horizon Mathematical Reasoning on MATH (Result and Process Metrics)
77.46Result Accuracy
StaRPO
Updated 6d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
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 | |
2026.04 | 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 |