Visual Reasoning on CRIT Natural Image
58.6EMQwen2.5-VL_CRIT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-VL_CRIT# Prm=7B2026.04 | 58.6 | 59.5 | |
| Qwen3-VL-Thinking# Prm=32B2026.04 | 43.1 | 44.2 | |
| Kimi-VL-Thinking# Prm=16B2026.04 | 33.8 | 35.3 | |
| Intern3-VL# Prm=8B2026.04 | 33.1 | 34.3 | |
| Qwen3-VL-Thinking# Prm=8B2026.04 | 31.8 | 32.9 | |
| GLM-4.1V-Thinking# Prm=9B2026.04 | 12 | 17.7 |