List your company

Advanced Mathematical Reasoning on AIME 25 (Accuracy)

19.9AIME 25 AccuracyNPG-Muse-8B
3.5727.81112.0516.289Aug 28, 2025

Evaluation results

MethodLinks
NPG-Muse-8BPass@k protocol=avg@642025.0819.9
Qwen2.5-14B-Instruct-1MPass@k protocol=avg@642025.0811.2
Qwen3-14B-BasePass@k protocol=avg@642025.0810.6
Qwen3-8B-BasePass@k protocol=avg@642025.0810.5
NPG-Muse-7BPass@k protocol=avg@642025.086.5
Qwen2.5-7B-Ins-1MPass@k protocol=avg@642025.084.2