#ReasoningModel

Hugging Face releases a 30B-A3B (Attention-Based) reasoning model targeting Olympiad-level math and physics problem solving. Achieves gold-medal performance on IPhO (physics) and IMO/USAMO (math) through test-time self-v…

Ning Ding's team releases a 30B-A3B reasoning model demonstrating gold-medal level performance on physics (IPhO) and math (IMO/USAMO) Olympiad benchmarks. The model employs test-time self-verification and refinement for…