List your company

Advanced Mathematical Reasoning on MATH 500 (Accuracy)

85.5AccuracyNPG-Muse-8B
63.6669.337580.67Aug 28, 2025

Evaluation results

MethodLinks
NPG-Muse-8BPass@k protocol=avg@82025.0885.5
Qwen2.5-14B-Instruct-1MPass@k protocol=avg@82025.0879
Qwen3-14B-BasePass@k protocol=avg@82025.0877.4
NPG-Muse-7BPass@k protocol=avg@82025.0870.9
Qwen2.5-7B-Ins-1MPass@k protocol=avg@82025.0869.6
Qwen3-8B-BasePass@k protocol=avg@82025.0864.5