List your company

Visual Reasoning on CRIT Scientific Paper

15.9Exact Match (EM)Qwen2.5-VL_CRIT
4.7727.66110.5513.439Apr 2, 2026

Evaluation results

MethodLinks
Qwen2.5-VL_CRIT# Prm=7B2026.0415.922.5
Qwen3-VL-Thinking# Prm=32B2026.048.410.5
Kimi-VL-Thinking# Prm=16B2026.048.112.3
Intern3-VL# Prm=8B2026.047.312.1
Qwen3-VL-Thinking# Prm=8B2026.047.39.6
GLM-4.1V-Thinking# Prm=9B2026.045.210.4