List your company

Mathematical Reasoning on AIME24 (Acc@16)

19.4Acc@16Self-Verify
2.246.69511.1515.605Feb 7, 2026

Evaluation results

MethodLinks
Self-VerifyModel=Qwen2.5-7B-Instruct2026.0219.41,575
GenerateModel=Qwen2.5-7B-Instruct2026.0216.37,053
Self-VerifyModel=Qwen2.5-3B-Instruct2026.029.22,755
GenerateModel=Qwen2.5-3B-Instruct2026.028.14,811
Self-VerifyModel=Qwen2.5-1.5B-Instruct2026.024.81,467
GenerateModel=Qwen2.5-1.5B-Instruct2026.022.92,580