STEM Reasoning on JEE Main 2025
87.8Pass@1Aryabhata 2
Evaluation Results
| Method | Links | |
|---|---|---|
| Aryabhata 2evaluation_protocol=4-sample mean2026.04 | 87.8 | |
| Gemini 2.5 Flashevaluation_protocol=4-sample mean2026.04 | 87.26 | |
| GPT-5 Minievaluation_protocol=4-sample mean2026.04 | 87.07 | |
| GPT-OSS-120Bevaluation_protocol=4-sample mean2026.04 | 85.61 | |
| Qwen3-30B-A3B (Thinking)evaluation_protocol=4-sample mean2026.04 | 84.89 | |
| Nemotron 3 Nano 30B A3Bevaluation_protocol=4-sample mean2026.04 | 82.89 | |
| GPT-OSS-20Bevaluation_protocol=4-sample mean2026.04 | 79.27 | |
| GPT-5 Nanoevaluation_protocol=4-sample mean2026.04 | 78.58 |