Reward Modeling on 3k-sample reward model (test)
1.1381MAEIEA-Summary-RM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| IEA-Summary-RMbase_model=Qwen3-0.6B2026.06 | 1.1381 | 66.54 | |
| GPT 4.1 mini2026.06 | 5.0013 | 14.2 | |
| Gemini 2.5 Flash-Lite2026.06 | 5.1923 | 9.83 | |
| Qwen3-0.6Bnumber of parameters=0.6B2026.06 | 7.2412 | 7.42 |