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

General VQA on MMStar

80.1Accuracy

Qwen3.5-Plus

Updated 23d ago

Evaluation Results

Method	Links
Qwen3.5-Plus 2026.06		80.1
K2.5 2026.06		79.8
Qwen3-VL-32B 2026.06		77.1
Qwen3-VL-32B 2026.06		76
Qwen3-VL-8B 2026.06		75.2
Opus-4.6 2026.06		74.5
Jigsaw-R1-8B 2026.04		74.3
EVE (Ours-8B-iter4) 2026.04		73.9
VisPlay-8B-iter3 2026.04		73.1
GPT-5.4 2026.06		72.7
Qwen3-VL-8B-Instruct 2026.04		72.1
Yuvion VL-32B 2026.06		71.3
Yuvion VL-32B 2026.06		71
Qwen2.5-VL-7B AIF 2026.04		70.9
Qwen2.5-VL-72B 2026.04		70.8
MM-Zero-8B-iter3 2026.04		70.7
Yuvion VL-8B 2026.06		70.5
Qwen3-VL-8B 2026.06		70.1
Qwen3-VL 2026.05		69.8
M2Note 2026.07		69.4
GPT-5 nano (high) 2026.04		68.6
Vanilla 2026.07		68.3
M2Note 2026.07		67.8
Qwen3-VL-Seg 2026.05		67.7
Qwen3-VL 2026.05		67.5
Vanilla 2026.07		66.5
InternVL3-9B 2026.04		66.3
Qwen-ViPER-7B 2026.04		66.2
LLaVA-OneVision-72B 2026.04		65.8
Yuvion VL-8B 2026.06		65.6
Vision-Zero 2026.07		65.2
Claude-3.5 Sonnet 2026.04		65.1
VisPlay 2026.07		65.1
InternVL-3.5 2026.05		65
CoT+M2Note 2026.07		64.9
GPT-4o 2026.04		64.7
GPT-4o-20240513 2026.04		64.7
M2Note 2026.07		64
Qwen2.5-VL-7B 2026.04		63.9
M2Note 2026.07		63.9
CoT 2026.07		62.9
Vanilla 2026.07		62.1
DPE 2026.07		62.1
Vanilla 2026.07		62.1
GPT-5 mini (minimal) 2026.04		61.3
FineViT-VL 2026.03		60.87
Intern3.5-VL 2026.03		57.33
Qwen3-VL 2026.03		56.6
Aquila-VL 2026.03		54.53
LLaVA-1.5-7B AIF 2026.04		39.5
LLaVA-1.5-7B 2026.04		33.1