General Chat on ArenaHard v1.0
82.75Win Rate
Direct-Likert
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 82.75 | |
2026.03 | 81.95 | |
2026.03 | 81.9 | |
2026.03 | 81.2 | |
2026.03 | 80.9 | |
2026.03 | 70.7 | |
2026.03 | 52.4 | |
2026.03 | 52.1 | |
2026.03 | 51.55 | |
2026.03 | 50.15 | |
2026.03 | 49.2 | |
2026.03 | 30.8 |