List your company

Math Reasoning on HMMT 25 (Feb)

22.29Pass@1XRPO
17.0918.4419.7921.14Oct 8, 2025

Evaluation results

MethodLinks
XRPOBackbone=Qwen3-1.7B2025.1022.2926.67
GSPOBackbone=Qwen3-1.7B2025.1021.2520
DAPOBackbone=Qwen3-1.7B2025.1020.4223.33
TPO-SBackbone=Qwen3-1.7B2025.1017.2920