DeepSeekMath-V2
685B open-weights (Apache 2.0) math prover built on DeepSeek-V3.2-Exp-Base; inference uses the DeepSeek-V3.2-Exp code. No first-party API endpoint verified. 'first' = first open-weights model at IMO-gold level (per the paper's claims).
- Input
- text
- Output
- text
- License
- apache-2.0
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | — | huggingface.co/deepseek-ai/DeepSeek-Math-V2 | — |
Notable capabilities (1)
- FIRST Self-verifiable proof generation: Generator trained against an LLM proof verifier and meta-verifier; reached IMO 2025 / CMO 2024 gold level and 118/120 on Putnam 2024 with scaled test-time compute. source
Download the weights from Hugging Face and serve them with the DeepSeek-V3.2-Exp inference stack. Source: https://huggingface.co/deepseek-ai/DeepSeek-Math-V2 · paper https://arxiv.org/abs/2511.22570
Timeline entry
- DeepSeekMath-V2: open-weights self-verifying prover reaches IMO 2025 gold level and 118/120 on Putnam 2024 ★★★★
DeepSeek released DeepSeekMath-V2 (685B parameters, built on DeepSeek-V3.2-Exp-Base, Apache 2.0). It is trained to write natural-language proofs and check them with an LLM verifier, including a meta-verifier. With scaled test-time compute it reached gold-medal level on IMO 2025 and CMO 2024 and…