Reward Modeling on PPE Correctness (test)
75PPE Corr
CE-RM-4B
Updated 3mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.01 | 75 | |
2026.01 | 73.1 | |
2026.01 | 72.9 | |
2026.01 | 71 | |
2026.01 | 70.3 | |
2026.01 | 69.8 | |
2026.01 | 69.7 | |
2026.01 | 67.9 | |
2026.01 | 65.9 | |
2026.01 | 65.7 | |
2026.01 | 65 | |
2026.01 | 62.4 | |
2026.01 | 61.9 | |
2026.01 | 60.4 | |
2026.01 | 60.2 | |
2026.01 | 60.1 | |
2026.01 | 59.8 | |
2026.01 | 59.3 | |
2026.01 | 59.2 | |
2026.01 | 57.9 | |
2026.01 | 57.6 | |
2026.01 | 56.6 | |
2026.01 | 55 | |
2026.01 | 53.8 | |
2026.01 | 48 | |
2026.01 | 42.6 |