Reward Modeling on preference-700K (test)
84.82Accuracy
Vanilla MoE
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 84.82 | |
2026.06 | 84.68 | |
2026.06 | 83.78 | |
2026.06 | 83.52 |
Vanilla MoE
| Method | Links | |
|---|---|---|
2026.06 | 84.82 | |
2026.06 | 84.68 | |
2026.06 | 83.78 | |
2026.06 | 83.52 |