Standardized Exam Solving on In-distribution (JEE Advanced 2025, NEET 2025, JEE Main 2025, JEE Main 2026)
90.23Pass@1 (%)Gemini 2.5 Flash
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Gemini 2.5 Flash2026.04 | 90.23 | 4,316.3 | 20.9 | |
| GPT-5 Mini2026.04 | 89.71 | 3,072.79 | 29.2 | |
| Aryabhata 22026.04 | 88.95 | 2,102.25 | 42.31 | |
| Qwen3-30B-A3Bmode=Thinking2026.04 | 88.55 | 4,555.93 | 19.44 | |
| GPT-OSS-120B2026.04 | 88.28 | 3,311.56 | 26.66 | |
| Nemotron 3 Nano 30B A3B2026.04 | 86.51 | 6,001.59 | 14.41 | |
| GPT-OSS-20B2026.04 | 83 | 5,293.04 | 15.68 | |
| GPT-5 Nano2026.04 | 79.89 | 5,861.08 | 13.63 |