Mathematical Reasoning on AIME (Pass@1 %)
90Pass@1 AccuracyGPT-OSS-120B
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-OSS-120BSampling Strategy=4-sample mean2026.04 | 90 | |
| GPT-OSS-20BSampling Strategy=4-sample mean2026.04 | 86.67 | |
| Aryabhata 2Sampling Strategy=4-sample mean2026.04 | 86.67 | |
| Qwen3-30B-A3B (Thinking)Sampling Strategy=4-sample mean2026.04 | 84.58 | |
| GPT-5 MiniSampling Strategy=4-sample mean2026.04 | 83.33 | |
| Nemotron 3 Nano 30B A3BSampling Strategy=4-sample mean2026.04 | 77.08 | |
| GPT-5 NanoSampling Strategy=4-sample mean2026.04 | 74.17 | |
| Gemini 2.5 FlashSampling Strategy=4-sample mean2026.04 | 66.61 |