MedXpertQA MM (Natomy) - Treatment: leaderboard
MedXpertQA multimodal accuracy restricted to treatment questions.
Metric: Accuracy (%). Source: www.natomy.com. Saturation forecast: Around February 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 90.18 | #9 |
| 2 | GPT-6 Astra | 87.05 | #6 |
| 3 | Claude Opus 5.5 (High) | 85.71 | #3 (Claude Opus 5.5) |
| 4 | Gemini 3.8 Flash | 85.49 | #30 |
| 5 | Gemini 3.1 Pro (Preview) | 82.59 | #64 |
| 6 | GPT-5.6 Sol | 82.37 | #22 |
| 7 | GPT-5.6 Terra | 78.12 | #40 |
| 8 | Claude Opus 5 | 77.68 | #16 |
| 9 | GPT-5.6 Luna (High) | 71.65 | #79 (GPT-5.6 Luna) |
| 10 | GPT-5.6 Luna (Medium) | 70.98 | #79 (GPT-5.6 Luna) |
| 11 | Claude Sonnet 5 | 62.72 | #65 |
No result here: #7 GPT-6.1 Sol, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=medxpertqa-mm-natomy-treatment · How It Works · Data refreshed daily, snapshot 2026-11-05.