AgentClinic: leaderboard
Clinical simulation benchmark for sequential diagnostic decision-making with multimodal patient interactions and compliance checks.
Metric: AgentClinic-MedQA diagnostic accuracy (imported). Source: agentclinic.github.io. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 51.6 | #438 |
| 2 | Mixtral 8x7B | 37.1 | #1143 |
| 3 | GPT-3.5 | 36.6 | #818 |
| 4 | GPT-4o | 34.2 | #343 |
| 5 | Llama 3 70B Instruct | 19 | #634 |
| 6 | Llama 2 70B Chat | 4.5 | #1237 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=agentclinic · How It Works · Data refreshed daily, snapshot 2026-10-20.