STEM Reasoning on NEET 2025
90Pass@1Gemini 2.5 Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 2.5 Flashevaluation_protocol=4-sample mean2026.04 | 90 | |
| GPT-5 Minievaluation_protocol=4-sample mean2026.04 | 87.33 | |
| Qwen3-30B-A3B (Thinking)evaluation_protocol=4-sample mean2026.04 | 86 | |
| GPT-OSS-120Bevaluation_protocol=4-sample mean2026.04 | 85.33 | |
| Aryabhata 2evaluation_protocol=4-sample mean2026.04 | 84.66 | |
| Nemotron 3 Nano 30B A3Bevaluation_protocol=4-sample mean2026.04 | 84 | |
| GPT-5 Nanoevaluation_protocol=4-sample mean2026.04 | 82.33 | |
| GPT-OSS-20Bevaluation_protocol=4-sample mean2026.04 | 81.33 |