Conversation Quality on MT-Bench English
8.73ScoreQwen3 235B A22B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3 235B A22B2026.06 | 8.73 | |
| GPT-4o2026.06 | 8.53 | |
| LuckyStar 111BQuantization=4-bit2026.06 | 8.5 | |
| Claude 3.7 Sonnet2026.06 | 8.47 | |
| LuckyStar 111B2026.06 | 8.45 | |
| Command A2026.06 | 8.34 |