List your company

Mathematical Reasoning on Olympiad (pass@1 and pass@32)

46.38Pass@1GRPO
21.128827.684434.2440.7956May 12, 2026

Evaluation results

MethodLinks
GRPOBackbone=Qwen3-8B-Base2026.0546.3859.33
FG-ExPOBackbone=Qwen3-8B-Base2026.0546.2560
GRPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0530.2354
FG-ExPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0529.3355.33
BaseBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0522.144