Thinking-with-Video
by tongjingqi · github.com/tongjingqi/Thinking-with-Video
We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that Sora-2 surpasses GPT5 by 10% on eyeballing puzzles and reaches 69% accuracy on MMMU.
Stars
★ 314
Forks
5
Language
Python
Category
LLM Tools
License
Apache-2.0
multimodal-reasoningsorasora2video-generationpythongptrag
Featured in
- Thinking with Video @ 03:35 · Nov 11, 2025