micro1 Medical Index: leaderboard
The publisher’s October 22 Medical Index is the equal mean of RealmPathology Mean Reward, PharmaBench Mean Score and WellnessBench Primary Pass. Only models evaluated on all three components are ranked. The composite combines different task and run protocols; it is not a new joint evaluation. Read the publisher’s rounded one-decimal overall score. Component scores are already covered and are not emitted again. Question access: Mixed component scored-set availability; the composite has no separate question set.
Metric: Equal component mean (0–100). Source: www.micro1.ai. Saturation forecast: Rough model projection: around 2026. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 71 | |
| 2 | Muse Wonder (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 70.8 | |
| 3 | Claude Sonnet 5.5 (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 70 | |
| 4 | Claude Opus 5.5 (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 68.4 | |
| 5 | Claude Fable 5.1 (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 68.2 | |
| 6 | Gemini 4 Argon (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 65.2 | |
| 7 | Grok 4.6 (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 64.1 | |
| 8 | Gemini 3.8 Flash (Benchmark Sweep Run: source=Micro1MedicalIndex; publisher composite; component protocols differ) | 60 |
Interactive version: theaggregate.ai/benchmark?slug=micro1-medical-index · How It Works · Data refreshed daily, snapshot 2026-11-06.