Multimodal Consistency Evaluation on ConBench benchmark leaderboard · SOTA2 Research

Multimodal Consistency Evaluation on ConBench

8.41ECEGPT-4o

Evaluation Results

Method	Links
GPT-4o2026.04		8.41	77.71	94.35	64.98
Qwen2.5-VL-7B2026.04		9.32	85.72	95.29	78.86
Phi-3.5-Vision2026.04		10.58	80.78	89.28	64.84
MiniCPM-V-2.62026.04		10.98	62.96	82.27	28
InternVL2.5-4B2026.04		12.26	81.84	95.11	74.24
GPT-4o2026.04		12.33	90.52	98.22	88.99
InternVL3.5-8B2026.04		13.12	65.12	85.89	35.86
InternVL2.5-4B2026.04		13.87	61.26	87.27	33.02
MiniCPM-V-2.62026.04		14.08	70.19	89.19	56.1
GPT-4o-mini2026.04		14.1	64.82	83.41	27.87
InternVL3.5-8B2026.04		15.98	83.33	94.08	73.11
GPT-4o-mini2026.04		19.71	80.46	93.01	69.62
Phi-3.5-Vision2026.04		20.33	63.14	72.65	10.32
Qwen2.5-VL-7B2026.04		38.65	35.91	74.9	-12.64