Hooshware
The o1 model uses reinforcement learning to 'think' via a chain of thought before generating an answer. It achieves state-of-the-art results on hard reasoning tasks, including math olympiads and PhD-level physics.
Hooshware signals & evidence
Recorded signals are separated from independent benchmarks and source claims.
Momentum reflects recent attention and activity. Hype and Reality appear only when recorded; missing values are never silently estimated.
Model intelligence
About o1 (OpenAI o1)
The o1 model uses reinforcement learning to 'think' via a chain of thought before generating an answer. It achieves state-of-the-art results on hard reasoning tasks, including math olympiads and PhD-level physics.
Discovery
Related models
No verified model relationships recorded yet.
Recorded facts
Technical profile
- License
- Proprietary
- Open weights
- Not recorded
- Input price / 1M
- Not recorded
- Output price / 1M
- Not recorded