Critique Quality Evaluation on Code
67.5Win RateRCO
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| RCOComparison Target=LLaMa-3-8B-Instruct + MSE + DPO2025.06 | 67.5 | 17.5 | 15 | 52.5 | |
| RCOComparison Target=LLaMa-3-70B-Instruct2025.06 | 50 | 37.5 | 12.5 | 37.5 | |
| RCOComparison Target=LLaMa-3-8B-Instruct + MSE + DPO2025.06 | 42.5 | 42.5 | 15 | 27.5 | |
| RCOComparison Target=LLaMa-3-8B-Instruct2025.06 | 40 | 50 | 10 | 30 | |
| RCOComparison Target=LLaMa-3-8B-Instruct2025.06 | 40 | 32.5 | 27.5 | 12.5 | |
| RCOComparison Target=LLaMa-3-70B-Instruct2025.06 | 30 | 42.5 | 27.5 | 2.5 |