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

Multimodal Reasoning on MMMU-Pro (Pass@1)

70.64Pass@1

GPT-5-Nano-High

Updated 1mo ago

Evaluation Results

Method	Links
GPT-5-Nano-High 2026.02		70.64
Qwen3-VL-8B-Thinking 2026.02		70.29
Qwen3-VL-8B-DeepVision 2026.02		70.29
MiMo-VL-7B-DeepVision 2026.02		69.19
Gemini 1.5 Pro 2025.05		68.8
Qwen3-VL-8B-Instruct 2026.02		67.69
Seed 1.5-VL 2025.05		67.6
MiMo-VL-7B-OpenMMReasoner 2026.02		66.82
OpenAI o1 2025.05		66.4
MiMo-VL-7B-MM-Eureka 2026.02		65.78
Gemini-2.5-Flash-Lite 2026.02		65.08
MiMo-VL-7B-RL-2508 2026.02		63.87
MiMo-VL-7B-MathBook 2026.02		63.47
MiMo-VL-7B-SFT-2508 2026.02		60.69
Seed 1.5-VL 2025.05		59.9
GPT-4o 2025.05		54.5
Qwen 2.5-VL 72B 2025.05		51.1
Claude 3.7 Sonnet 2025.05		50.1