Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Reasoning on MMMU-Pro (test)
Loading...
55
Accuracy
Claude-3.5 Sonnet
18.184
27.742
37.3
46.858
Apr 6, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Claude-3.5 Sonnet
2026.04
55
GPT-4o
2026.04
54
Gemini-1.5-Pro
2026.04
49.4
InternVL2.5-8B
2026.04
38.2
Qwen2.5-VL-7B + Saliency-R1
Training Stage=Salienc...
2026.04
37.6
Qwen2.5-VL-7B
Training Stage=Base
2026.04
36.2
Qwen2.5-VL-7B + SFT
Training Stage=SFT
2026.04
35.5
InternVL2-8B
2026.04
32.5
Qwen2.5-VL-3B + Saliency-R1
Training Stage=Salienc...
2026.04
31.1
Qwen2.5-VL-3B
Training Stage=Base
2026.04
30.8
Qwen2.5-VL-3B + SFT
Training Stage=SFT
2026.04
29.9
MiniCPM-V-2.6-8B
2026.04
27.2
Insight-V-8B
2026.04
24.9
MiniCPM-Llama-V-2.5-8B
2026.04
19.6
Feedback
Search any
task
Search any
task