---
id: "2025-11-27-deepseekmath-v2"
url: "https://postcutoff.com/e/2025-11-27-deepseekmath-v2/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2025-11-27"
date_precision: day
category: open-source
importance: 4
confidence: high
status: [Confirmed]
sources: 2
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2025-11-27-deepseekmath-v2/

# 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 scored 118/120 on Putnam 2024. It was the first openly downloadable model at IMO-gold level.

## Key facts
- Paper: arXiv 2511.22570 'DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning' (27 Nov 2025)
- 685B parameters; base DeepSeek-V3.2-Exp-Base; Apache 2.0 weights on Hugging Face
- Gold-level scores on IMO 2025 and CMO 2024; 118/120 on Putnam 2024 (scaled test-time compute)
- Method: faithful LLM proof verifier plus meta-verification to cut hallucinated issues; the generator is rewarded for finding and fixing its own errors; verifier compute is scaled to auto-label hard proofs without human annotation

## What happened

Four months after closed models from Google DeepMind and OpenAI reached IMO gold, DeepSeek released open weights for a proof-writing model at the same level. It made self-verification (generator + verifier + meta-verifier) the main training signal instead of final-answer rewards.

## Why it matters

It made olympiad-level natural-language proof generation reproducible outside the big US labs. The generate-then-verify recipe became a common pattern in 2026 AI-for-math systems.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [arXiv 2511.22570](https://arxiv.org/abs/2511.22570) (arxiv.org, paper)
2. [Hugging Face: deepseek-ai/DeepSeek-Math-V2](https://huggingface.co/deepseek-ai/DeepSeek-Math-V2) (huggingface.co, code)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2025-12-06: [AxiomProver produces machine-checked Lean proofs for all 12 Putnam 2025 problems](https://postcutoff.com/e/2025-12-06-axiomprover-putnam-2025/index.md)
- 2025-07-21: [AI systems reach gold-medal level at the International Mathematical Olympiad](https://postcutoff.com/e/2025-07-21-imo-gold-ai/index.md)
- 2024-12-26: [DeepSeek-V3: frontier-level open model trained for ~$5.6M in GPU time](https://postcutoff.com/e/2024-12-26-deepseek-v3/index.md)
- Models: [DeepSeekMath-V2](https://postcutoff.com/m/deepseekmath-v2/) (`deepseekmath-v2`)