AI models
rStar-Math (Qwen2-Math-7B base)
Parameters
7B
Published
Aug 1, 2025
rStar-Math (Qwen2-Math-7B base) is an AI model developed by Microsoft Research Asia, Peking University and Tsinghua University (China), first published in August 2025. It works in the language domain, on tasks such as language modeling/generation and mathematical reasoning.
Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters. Training ran on 80 NVIDIA H100 SXM5 80GB.
Access: Unreleased. Its weights are not openly released. It is built on top of Qwen2-Math-7B. The reference paper has 308 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Microsoft Research Asia, Peking University, Tsinghua University
- Country of organization
- China
- Domain
- Language
- Task
- Language modeling/generation, Mathematical reasoning
- Compute estimation method
- Operation counting
- Parameters
- 7,000,000,000
- Training hardware
- NVIDIA H100 SXM5 80GB
- Chips used
- 80
- Training power draw
- 109.5 kW
- Model accessibility
- Unreleased
- Open weights
- No
- Base model
- Qwen2-Math-7B
- Citations
- 308
- Epoch confidence
- Confident
More from Microsoft Research Asia,Peking University,Tsinghua University
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models