AI models
DeepSeekMath 7B
Training compute
10²³ FLOP
Parameters
7B
Published
Feb 5, 2024
DeepSeekMath 7B is an AI model developed by DeepSeek, Tsinghua University and Peking University (China), first published in February 2024. It works in the language domain, on tasks such as quantitative reasoning.
Training it took an estimated 10²³ FLOP of compute (estimation method: operation counting). The model has 7,000,000,000 parameters. It was trained on roughly 500B datapoints.
Access: Open weights (restricted use). Its weights are openly available. It is built on top of DeepSeek Coder 6.7B. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- DeepSeek, Tsinghua University, Peking University
- Country of organization
- China
- Domain
- Language
- Task
- Quantitative reasoning
- Training compute
- 10²³ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 7,000,000,000
- Dataset size
- 500B
- Model accessibility
- Open weights (restricted use)
- Open weights
- Yes
- Base model
- DeepSeek Coder 6.7B
- Epoch confidence
- Confident
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