PatientAgentBench - Clinical Helpfulness: leaderboard

Metric: Mean clinical helpfulness 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: Around December 2026. 10 models tracked.

Top models

#ModelScore
1Claude Opus 4.84.23
2GPT-5.54.19
3Claude Sonnet 54.14
4GPT-5.44.04
5Gemini 3 Flash3.82
6Qwen 3 235B A22B3.68
7Gemini 3.1 Pro (Preview)3.66
8GPT-OSS-120B3.63
9Claude Haiku 4.53.63

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