Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Understanding and Reasoning on MMMU
Loading...
59
Accuracy
PTA-GRPO
32.584
39.442
46.3
53.158
Jun 12, 2024
Aug 30, 2024
Nov 18, 2024
Feb 5, 2025
Apr 26, 2025
Jul 14, 2025
Oct 2, 2025
Accuracy
Updated 7d ago
Evaluation Results
Method
Method
Links
Accuracy
PTA-GRPO
Base Model=Qwen2.5-7B-VL
2025.10
59
SRPO
Base Model=Qwen2.5-7B-VL
2025.10
57.1
GPT-4V
2024.06
56.8
Base
Base Model=Qwen2.5-7B-VL
2025.10
54.3
LLaVA-1.5-LLaMA3-8B
Base Model=LLaMA3, Mod...
2024.06
45.2
LLaVA-1.5-13B
Model size=13B
2024.06
36.4
LLaVA-1.5-7B
Model size=7B
2024.06
33.6
Feedback
Search any
task
Search any
task