AlphaUncommon
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.
- Owner
- tongjingqi (personal account)
- Stars
- Stars: 320
- Forks
- Forks: 6
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Topics
- multimodal-reasoningsorasora2video-generation
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by tongjingqi
All 3 repos by tongjingqi- tongjingqi/AI-Can-Learn-Scientific-TasteStars: 436Alpha
- tongjingqi/Game-RLStars: 162PythonPrototype
Nearby in Python
All Python repos- f3rb123/kill_flutterStars: 320PythonAlpha
- zeroweight-ai/ZeroTTSStars: 320PythonAlpha
- mater1996/travel-planningStars: 320PythonAlpha
- basho/riak-python-clientStars: 320PythonAlpha
- duckduckgo/zeroclickinfo-fatheadStars: 320PythonAlpha
- jazzband/django-queued-storageStars: 320PythonAlpha