DeepSeekMath-V2
IMO Gold level reasoning, fully open.
0.0
34 upvotes|0 reviews|1 stars

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
0.00 reviews
5
0
4
0
3
0
2
0
1
0
No reviews yet. Be the first!
Created byParker Hernandez
Making the web a better place
647Views
0
Comments360Burned
Review Budget
107credits
Reviewers earn credits for providing high-quality feedback.