PatientAgentBench - Task Completion: leaderboard

Metric: Mean task completion rubric score (1-5); 1,200 synthetic patient conversations of up to 15 turns with a simulated patient, the model inside the benchmark's baseline ReAct agent harness with 15 healthcare sandbox tools; jury of Claude Opus 4.8 and GPT-5.5 judges scoring clinician-grounded rubrics on a 1 to 5 scale; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.

Top models

#ModelScore
1Claude Sonnet 54.86
2GPT-5.44.85
3Claude Opus 4.84.84
4GPT-5.54.79
5Gemini 3 Flash4.69
6Gemini 3.1 Pro (Preview)4.65
7GPT-OSS-120B4.56
8Claude Haiku 4.54.52
9Qwen 3 235B A22B4.49

Interactive version: theaggregate.ai/benchmark?slug=patientagentbench-task-completion · How It Works · Data refreshed daily, snapshot 2026-09-29.