LLM win-rate estimation ranking on LLM benchmark (Appendix)
1Spearman Correlation
AIPW-EM
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 1 | 100 | 0 | |
2026.04 | 1 | 100 | 0 | |
2026.04 | 1 | 100 | 0 | |
2026.04 | 1 | 100 | 0 | |
2026.04 | 1 | 100 | 0 | |
2026.04 | 1 | 100 | 0 | |
2026.04 | 0.75 | 87.5 | 0.003 | |
2026.04 | 0.5 | 75 | 0.006 | |
2026.04 | 0.5 | 75 | 0.006 | |
2026.04 | 0.5 | 75 | 0.006 | |
2026.04 | 0.25 | 62.5 | 0.01 | |
2026.04 | 0.25 | 62.5 | 0.01 | |
2026.04 | 0.25 | 62.5 | 0.01 | |
2026.04 | 0 | 50 | 0.013 |