Share your thoughts, 1 month free Claude Pro on usSee more

Multimodal Reasoning on MMStar (ACC%, S, I)

67.1Accuracy (ACC%)

Qwen3-VL-30B+VRGA

Updated 1mo ago

Evaluation Results

Method	Links
Qwen3-VL-30B+VRGA 2026.03		67.1	0.522	0.543
Qwen3-VL-30B 2026.03		66.1	0.521	0.542
Qwen2-VL-7B 2026.03		52.37	0.419	0.499
Qwen2-VL-7B+VRGA 2026.03		51.07	0.405	0.513
Qwen2.5-VL-3B+VRGA 2026.03		50.93	0.441	0.383
Qwen2-VL-7B+CCOT 2026.03		50.06	-	-
Qwen2.5-VL-3B 2026.03		49.8	0.436	0.382
Qwen2.5-VL-7B+VRGA 2026.03		48.73	0.388	0.569
Qwen2.5-VL-7B 2026.03		48.53	0.389	0.557
Qwen2.5-VL-3B+CCOT 2026.03		46.27	-	-
Qwen2-VL-7B+ICOT 2026.03		42.27	0.358	0.523