Reward Modeling on FollowBench (Accuracy)
89.9Accuracy
RM-R1-14B (DeepSeek-Dist)
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 89.9 | |
2026.02 | 89.2 | |
2026.02 | 87.4 | |
2026.02 | 86 | |
2026.02 | 85.7 | |
2026.02 | 85.7 | |
2026.02 | 84.9 | |
2026.02 | 84 | |
2026.02 | 83.2 | |
2026.02 | 81.7 | |
2026.02 | 81.5 | |
2026.02 | 79.8 | |
2026.02 | 76.1 | |
2026.02 | 69.7 | |
2026.02 | 65.5 | |
2026.02 | 63 | |
2026.02 | 56.3 |