AgentClinic — leaderboard

Clinical simulation benchmark for sequential diagnostic decision-making with multimodal patient interactions and compliance checks.

Metric: AgentClinic-MedQA diagnostic accuracy (self-reported). Source: benchmarklist.com. Status: saturation imminent. 7 models tracked.

Top models

#ModelScore
1GPT-451.6
2Mixtral 8x7B37.1
3GPT-3.536.6
4GPT-4o34.2
5Llama 3 70B Instruct19
6Llama 2 70B Chat4.5

Interactive version: theaggregate.ai/benchmark?slug=agentclinic · How the rankings work · Data refreshed daily, snapshot 2026-07-22.