DeepSeekMath-V2 logo

DeepSeekMath-V2

IMO Gold level reasoning, fully open.

0.0
34 upvotes|0 reviews|1 stars
DeepSeekMath-V2 product shot 1
1 / 4

DeepSeekMath-V2 is a new open-source model specialized in mathematical reasoning. It introduces a self-verification mechanism where the model acts as both generator and verifier to refine its own proofs. It achieved Gold-level scores in IMO 2025 and a near-perfect 118/120 in Putnam 2024.

Reviews

0.0
0 reviews
5
0
4
0
3
0
2
0
1
0

No reviews yet. Be the first!

Sign in to Review

Join the community to give feedback and earn credits.

Sign In
Parker Hernandez
Created byParker Hernandez

Making the web a better place

647Views
0
Comments
360Burned
Review Budget
107credits

Reviewers earn credits for providing high-quality feedback.