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.
DeepSeek-Math-V2 huggingface.co is an AI model on huggingface.co that provides DeepSeek-Math-V2's model effect (), which can be used instantly with this deepseek-ai DeepSeek-Math-V2 model. huggingface.co supports a free trial of the DeepSeek-Math-V2 model, and also provides paid use of the DeepSeek-Math-V2. Support call DeepSeek-Math-V2 model through api, including Node.js, Python, http.
DeepSeek-Math-V2 huggingface.co is an online trial and call api platform, which integrates DeepSeek-Math-V2's modeling effects, including api services, and provides a free online trial of DeepSeek-Math-V2, you can try DeepSeek-Math-V2 online for free by clicking the link below.
deepseek-ai DeepSeek-Math-V2 online free url in huggingface.co:
DeepSeek-Math-V2 is an open source model from GitHub that offers a free installation service, and any user can find DeepSeek-Math-V2 on GitHub to install. At the same time, huggingface.co provides the effect of DeepSeek-Math-V2 install, users can directly use DeepSeek-Math-V2 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.