Helpful Dialogue on Anthropic HH-RLHF helpful core250 (test)
18.93Reward ScoreTEA
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| TEAN=1282026.05 | 18.93 | 1.817 | 1.336 | 67.2 | 2.4 | 30.4 | |
| GRPON=2562026.05 | 18.354 | — | — | — | — | — | |
| TEAN=2562026.05 | 18.354 | 1.8 | 1.264 | 64.8 | 3.6 | 31.6 | |
| TEAN=642026.05 | 17.674 | 1.94 | 1.502 | 72.8 | 2 | 25.2 | |
| GRPON=1282026.05 | 17.113 | — | — | — | — | — | |
| TEAN=322026.05 | 16.224 | 1.98 | 1.605 | 75.2 | 2.4 | 22.4 | |
| GRPON=642026.05 | 15.734 | — | — | — | — | — | |
| TEAN=162026.05 | 14.555 | 1.911 | 1.583 | 77.6 | 2 | 20.4 | |
| GRPON=322026.05 | 14.244 | — | — | — | — | — | |
| GRPON=162026.05 | 12.644 | — | — | — | — | — | |
| TEAN=82026.05 | 12.55 | 1.792 | 1.482 | 78.4 | 2 | 19.6 | |
| GRPON=82026.05 | 10.758 | — | — | — | — | — | |
| TEAN=42026.05 | 10.12 | 1.634 | 1.321 | 78 | 2 | 20 | |
| GRPON=42026.05 | 8.485 | — | — | — | — | — | |
| TEAN=22026.05 | 7.081 | 1.375 | 1.071 | 76.8 | 2 | 21.2 | |
| GRPON=22026.05 | 5.707 | — | — | — | — | — | |
| TEAN=12026.05 | 3.017 | 0.978 | 0.683 | 71.6 | 2 | 26.4 | |
| GRPON=12026.05 | 2.039 | — | — | — | — | — |