Conversation Evaluation on CRSArena Eval (All)
0.918Pearson Correlation (r)FACE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FACE2026.06 | 0.918 | 0.838 | |
| LLMDirecttype=reference-free2026.06 | 0.868 | 0.806 | |
| G-Evaltype=reference-free2026.06 | 0.85 | 0.833 | |
| Distinct-3n-gram=32026.06 | 0.68 | 0.798 | |
| Distinct-4n-gram=42026.06 | 0.622 | 0.771 | |
| iEvaLMattrmode=attr2026.06 | 0.575 | 0.517 | |
| iEvaLMfreemode=free2026.06 | 0.257 | 0.184 | |
| R@10type=reference-based2026.06 | -0.134 | 0.064 | |
| R@1type=reference-based2026.06 | -0.142 | 0.075 |