List your company

Math Reasoning on BRUMO'25

47.39Pass@1XRPO
37.000439.697742.39545.0923Oct 8, 2025

Evaluation results

MethodLinks
XRPOBackbone=Qwen3-1.7B2025.1047.3960
GSPOBackbone=Qwen3-1.7B2025.1045.256.67
DAPOBackbone=Qwen3-1.7B2025.1039.943.33
TPO-SBackbone=Qwen3-1.7B2025.1037.446.67