Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Real-world Multimodal Evaluation on MME-RW (test)
Loading...
62.9
Overall Score
Qwen2.5-VL-7B + Saliency-R1
37.212
43.881
50.55
57.219
Apr 6, 2026
Overall Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Overall Score
Qwen2.5-VL-7B + Saliency-R1
Training Stage=Salienc...
2026.04
62.9
Qwen2.5-VL-7B + SFT
Training Stage=SFT
2026.04
60.6
Qwen2.5-VL-7B
Training Stage=Base
2026.04
58.7
InternVL2.5-8B
2026.04
58.1
Qwen2.5-VL-3B + Saliency-R1
Training Stage=Salienc...
2026.04
57.7
LLaVA-OneVision-7B
2026.04
57.4
Qwen2.5-VL-3B + SFT
Training Stage=SFT
2026.04
56
InternVL2-8B
2026.04
53.5
Qwen2.5-VL-3B
Training Stage=Base
2026.04
52
Claude-3.5 Sonnet
2026.04
51.6
IXC-2.5
2026.04
50
MiniCPM-Llama-V-2.5-8B
2026.04
45.6
GPT-4o
2026.04
45.2
Cambrain-1-8B
2026.04
42.7
Gemini-1.5-Pro
2026.04
38.2
Feedback
Search any
task
Search any
task