Agent evaluation on VSM full (evaluation)
85.96Average RatingClaude-Opus 4.6
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude-Opus 4.6Model=Claude-Opus 4.62026.04 | 85.96 | 0.86 | 38,594 | |
| GLM-5Model=GLM-52026.04 | 83.88 | 3.92 | 27,580 | |
| Qwen3-30B-A3B-Thinking-2507Model=Qwen3-30B-A3B-Thinking-25072026.04 | 72.66 | 2.1 | 43,482 | |
| Ministral-3-14B-Reasoning-2512Model=Ministral-3-14B-Reasoning-25122026.04 | 57.34 | 6.64 | 39,819 |