SciEval - Life Sciences: leaderboard
SciEval multimodal scientific-reasoning leaderboard — life-sciences-discipline accuracy.
Metric: Life Sciences (%). Source: huggingface.co. Saturation forecast: Around January 2028. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 | 61.57 | #124 |
| 2 | GPT-5.1 | 60.54 | #135 |
| 3 | GPT-5 | 59.49 | #98 |
| 4 | Qwen 3 VL 235B A22B | 56.69 | #238 |
| 5 | GPT-4o | 54.46 | #343 |
| 6 | GLM-4.5V | 54.11 | #346 |
| 7 | Intern-S1 | 53.7 | #285 |
| 8 | Gemini 3 Pro | 49.2 | #80 |
| 9 | Claude Sonnet 4.5 | 43.86 | #142 |
| 10 | Grok 2 (1212) | 43.44 | #496 |
| 11 | Llama 4 Maverick | 42.92 | #464 |
| 12 | Kimi K2 | 41.1 | #243 |
| 13 | Qwen 3 Max | 38.95 | #208 |
| 14 | Gemini 2.5 Flash | 35.61 | #245 |
| 15 | Gemini 2.5 Pro | 34.85 | #152 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=scieval-life-sciences · How It Works · Data refreshed daily, snapshot 2026-10-20.