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

General Multimodal Understanding on MM*

73.6Accuracy

Gemini-2.5-Pro

Updated 25d ago

Evaluation Results

Method	Links
Gemini-2.5-Pro 2026.06		73.6
GPT-5 2026.06		73
Qwen3-VL-8B 2026.06		70.9
TACO (Ours-7B) 2026.06		69.3
Qwen2.5-VL-32B 2026.06		69.1
InternVL3-8B 2026.06		68.5
CodeV-RL-7B 2026.06		67.6
DeepEyes-v2-7B 2026.06		66.1
Thyme-7B 2026.06		65.9
GPT-4o 2026.06		65.7
PyVision-RL-7B 2026.06		65.6
DeepEyes-7B 2026.06		65.3
Qwen2.5-VL-7B 2026.06		64.7
Pixel-Reasoner-7B 2026.06		64.7
Mini-o3-7B 2026.06		63.8
MathCoder-VL-8B 2026.06		62.5
LLaVA-OneVision-7B 2026.06		61.7