OREAL-32B
Open in the interactive archive →
Download the covers: Floppy card · VHS cover · Vinyl cover
A to Z
- A · App
- No
- B · Built By
- Shanghai AI Laboratory/SenseTime
- C · CEO & Politics
- [UNKNOWN]
- D · Date
- 2025
- E · Expertise
- Intermediate+
- F · Free Tier
- Yes
- G · Generates
- Text only
- H · Deployment
- Cloud + Local (open weights)
- I · Inputs
- Text
- J · Jurisdiction
- China
- K · Key Staffers
- Tang Xiao-ou (Founder SenseTime)
- L · Languages
- Chinese-primary
- M · Model Type
- LLM
- N · Safety Issues
- None reported
- O · Open Source
- Yes — open weights
- P · Pricing
- Free (open weights, Apache 2.0)
- Q · AIDb Rating
- 4/10 · AIDb v2.0 (rule-based): Capability 4/10 · Currency 4/10 · Access 2/10 · Significance 4/10 → 3.70
- R · What Makes It Special
- OREAL-32B, an open (Apache 2.0) 32B math-reasoning model from the InternLM team, trained with OREAL (Outcome REwArd-based reinforcement Learning), an RL method for tasks with only right-or-wrong rewards that clones best-of-N correct samples, reshapes rewards for wrong ones and uses a token-level reward model to find key reasoning steps; it scores 95.0 pass@1 on MATH-500, above earlier distillation-trained 32B models, and 60.0 on AIME 2024. A 7B sibling and SFT versions are also open.
- S · Stock / Status
- Government-backed research lab (Shanghai AI Laboratory)
- T · Training Cutoff
- [UNKNOWN]
- U · Users
- [UNKNOWN]
- V · Voice Chat
- No
- W · Weights
- Downloadable
- X · X Handle
- @SenseTime_AI
- Y · Year Founded
- [UNKNOWN]
- Z · Bottom Line
- Open-weights LLM from Shanghai AI Laboratory/SenseTime, released 2025.
Data completeness 85% · Last verified 2026-06-11 · Primary source ↗
Cite this
“OREAL-32B.” AIDb — The AI Database. Verified 2026-06-11. https://theaidatabase.com/m/shanghai-ai-laboratory-sensetime-oreal-32b.html