https://huggingface.co/deepseek-ai/DeepSeek-Math-V2

Hugging Face's logo Hugging Face
[                    ]

  * Models
  * Datasets
  * Spaces
  * Community
  * Docs
  * Enterprise
  * Pricing
  * 
  * -----------------------------------------------------------------
  * Log In
  * Sign Up

[xMBly9PUMp]
deepseek-ai
/
DeepSeek-Math-V2
like 563
Follow
[xMBly9PUMp] DeepSeek 108k

 
Text Generation
 
Transformers
 
Safetensors
 
deepseek_v32
 
conversational
 
fp8
License: apache-2.0
Model card Files Files and versions
xet
Community
5
Deploy
Use this model

  * DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
      + 1. Introduction
      + 2. Evaluation Results
      + 4. Quick Start
      + 6. License
      + 7. Citation
      + 8. Contact

                             DeepSeek-V3
---------------------------------------------------------------------
                     Homepage Chat Hugging Face
                    Discord Wechat Twitter Follow
                               License

 DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

 1. Introduction

Large language models have made significant progress in mathematical
reasoning, which serves as an important testbed for AI and could
impact scientific research if further advanced. By scaling reasoning
with reinforcement learning that rewards correct final answers, LLMs
have improved from poor performance to saturating quantitative
reasoning competitions like AIME and HMMT in one year. However, this
approach faces fundamental limitations. Pursuing higher final answer
accuracy doesn't address a key issue: correct answers don't guarantee
correct reasoning. Moreover, many mathematical tasks like theorem
proving require rigorous step-by-step derivation rather than
numerical answers, making final answer rewards inapplicable. To push
the limits of deep reasoning, we believe it is necessary to verify
the comprehensiveness and rigor of mathematical reasoning.
Self-verification is particularly important for scaling test-time
compute, especially for open problems without known solutions.
Towards self-verifiable mathematical reasoning, we investigate how to
train an accurate and faithful LLM-based verifier for theorem
proving. We then train a proof generator using the verifier as the
reward model, and incentivize the generator to identify and resolve
as many issues as possible in their own proofs before finalizing
them. To maintain the generation-verification gap as the generator
becomes stronger, we propose to scale verification compute to
automatically label new hard-to-verify proofs, creating training data
to further improve the verifier. Our resulting model,
DeepSeekMath-V2, demonstrates strong theorem-proving capabilities,
achieving gold-level scores on IMO 2025 and CMO 2024 and a
near-perfect 118/120 on Putnam 2024 with scaled test-time compute.
While much work remains, these results suggest that self-verifiable
mathematical reasoning is a feasible research direction that may help
develop more capable mathematical AI systems.

 2. Evaluation Results

Below are evaluation results on IMO-ProofBench (developed by the
DeepMind team behind DeepThink IMO-Gold) and recent mathematics
competitions including IMO 2025, CMO 2024, and Putnam 2024.

IMO-ProofBench

                          [IMO-ProofBench]

---------------------------------------------------------------------

Mathematics Competitions

                               [Comp]

 4. Quick Start

DeepSeekMath-V2 is built on top of DeepSeek-V3.2-Exp-Base. For
inference support, please refer to the DeepSeek-V3.2-Exp github
repository.

 6. License

This repository and the model weights are licensed under the Apache
License, Version 2.0 (Apache 2.0).

 7. Citation

@misc{deepseek-math-v2,
  author = {Zhihong Shao, Yuxiang Luo, Chengda Lu, Z.Z. Ren, Jiewen Hu, Tian Ye, Zhibin Gou, Shirong Ma, Xiaokang Zhang},
  title = {DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning},
  year = {2025},
}

 8. Contact

If you have any questions, please raise an issue or contact us at
service@deepseek.com.

Downloads last month
    4,434

Safetensors 
Model size
685B params
Tensor type
BF16
*
F8_E4M3
*
F32
*

Chat template

Files info

Inference Providers NEW
 
Text Generation
This model isn't deployed by any Inference Provider.  98 Ask for
provider support
Model tree for deepseek-ai/DeepSeek-Math-V2  

Unable to build the model tree, the base model loops to the model
itself. Learn more.

Collection including deepseek-ai/DeepSeek-Math-V2

DeepSeek-Math

Collection
DeepSeek Math series * 6 items * Updated 5 days ago * 43
System theme
Company
TOS Privacy About Jobs  
Website
Models Datasets Spaces Pricing Docs