List your company

Mathematical Reasoning on AIME (Pass@1 %)

90Pass@1 AccuracyGPT-OSS-120B
65.674471.989778.30584.6203Apr 10, 2026

Evaluation results

MethodLinks
GPT-OSS-120BSampling Strategy=4-sample mean2026.0490
GPT-OSS-20BSampling Strategy=4-sample mean2026.0486.67
Aryabhata 2Sampling Strategy=4-sample mean2026.0486.67
Qwen3-30B-A3B (Thinking)Sampling Strategy=4-sample mean2026.0484.58
GPT-5 MiniSampling Strategy=4-sample mean2026.0483.33
Nemotron 3 Nano 30B A3BSampling Strategy=4-sample mean2026.0477.08
GPT-5 NanoSampling Strategy=4-sample mean2026.0474.17
Gemini 2.5 FlashSampling Strategy=4-sample mean2026.0466.61