List your company

Mathematical Reasoning on BRUMO 2025 (avg@32)

63.3Avg@32 ScoreGSPO
4.0219.4134.850.19May 8, 2026

Evaluation results

MethodLinks
GSPOBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.0563.3
CTPOBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.0563
GRPOBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.0561.9
CTPOBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.0559.7
GSPOBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.0556.8
GRPOBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.0553.1
BaseBase Model=Qwen3-14B, Reasoning Setting=Tool-integrated2026.057
BaseBase Model=Qwen3-4B, Reasoning Setting=Tool-integrated2026.056.3