List your company

Mathematical Reasoning on MATH 500 (P@1)

83.8P@1GRPO w/ OAR-P
49.89658.69867.576.302Jan 12, 2026

Evaluation results

MethodLinks
GRPO w/ OAR-PBackbone=Qwen2.5-Math-7B2026.0183.8
GRPO w/ OAR-GBackbone=Qwen2.5-Math-7B2026.0183
GRPO w/ KTAEBackbone=Qwen2.5-Math-7B2026.0182.4
GRPO w/ Entropy AdvBackbone=Qwen2.5-Math-7B2026.0181.7
GRPOBackbone=Qwen2.5-Math-7B2026.0180.8
GRPO w/ Random AdvBackbone=Qwen2.5-Math-7B2026.0179.8
GRPO w/ OAR-GBackbone=Qwen2.5-7B2026.0178.7
GRPO w/ OAR-PBackbone=Qwen2.5-7B2026.0178.4
GRPO w/ Entropy AdvBackbone=Qwen2.5-7B2026.0177.2
GRPOBackbone=Qwen2.5-7B2026.0175.8
GRPO w/ Random AdvBackbone=Qwen2.5-7B2026.0175.2
Qwen2.5-7BBackbone=Qwen2.5-7B2026.0152.7
Qwen2.5-Math-7BBackbone=Qwen2.5-Math-7B2026.0151.2