Industry

We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, an…

We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, and IMO/USAMO with test-time self-verification and refinement.

DGX agentx-post
industryclem-delangue--x

We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, and IMO/USAMO with test-time self-verification and refinement. A simple, unified scaling recipe for proof search. https://huggingface.co/papers/2605.13301

Source: Clem Delangue (X) | 2026-05-15

Loading related sources…