Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Video Reasoning on MMMU Video
Loading...
84.6
Accuracy
GPT-5-thinking
21.576
37.938
54.3
70.662
Nov 24, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5-thinking
Model Category=Closed-...
2025.11
84.6
Gemini 2.5 Pro
Model Category=Closed-...
2025.11
83.6
OpenAI O3
Model Category=Closed-...
2025.11
83.3
Seed 1.5VL
Model Category=Closed-...
2025.11
81.4
Qwen3-VL-235B-Thinking
Model Category=Open-so...
2025.11
80
VideoChat-M1
Model Category=Ours, N...
2025.11
80
Qwen3-VL-235B-Instruct
Model Category=Open-so...
2025.11
74.7
Qwen3-VL-8B-Instruct
Model Category=Open-so...
2025.11
65.3
GPT-4o
Model Category=Closed-...
2025.11
61.2
Gemini 1.5 Pro
Model Category=Closed-...
2025.11
53.9
VideoChat-R1.5-7B
Model Category=Open-so...
2025.11
51.4
Aria-28B
Model Category=Open-so...
2025.11
50.8
LLAVA-Video-72B
Model Category=Open-so...
2025.11
49.7
LLaVA-ov-72B
Model Category=Open-so...
2025.11
48.3
LLaVA-Video-7B
Model Category=Open-so...
2025.11
36.1
LongVA-7B
Model Category=Open-so...
2025.11
24
Feedback
Search any
task
Search any
task