List your company

Mathematical Reasoning on AIME 25, AIME 26, BRUMO 25, HMMT 25 Aggregate

58.8Average Score @ 32CTPO
1.70416.52731.3546.173May 8, 2026

Evaluation results

MethodLinks
CTPOBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.0558.8
GSPOBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.0555.5
GRPOBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.0554.6
CTPOBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.0551.4
GSPOBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.0547.7
GRPOBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.0543.2
BaseBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.056.1
BaseBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.053.9