HealthGPT-Pro-4B: benchmark results

Provider: Other.

Aggregate Rating 1508 ± 52, rank #2175 of 10552 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ObGynLongBench - History-Level EHR - L3 Long-Horizon Reasoning57.3Accuracy (%)59.4
MedPIC-Bench - Rule Deactivation41.2Accuracy (%)55.6
ObGynLongBench - History-Level EHR57.1Accuracy (%; full pre-decision EHR history)25
ObGynLongBench - History-Level EHR - L1 Single Evidence59Accuracy (%)25
ObGynLongBench - History-Level EHR - L2 Multi-Source Integration56.1Accuracy (%)25
ObGynLongBench - Visit-Level EHR54.1Accuracy (%; same-day visit records)25
MedPIC-Bench - Counterfactual Pair11.2Both-correct pair rate (%)24.1
MedPIC-Bench - Counterfactual33.3Accuracy (%)22.2
ObGynLongBench - Evidence-Only69.6Accuracy (%; supporting evidence only)18.8
MedPIC-Bench - Rule Activation36.6Accuracy (%)1.9
MedPIC-Bench - Guideline-Following37.7Accuracy (%)0
MedPIC-Bench - Overall36Accuracy (%)0

Interactive version: theaggregate.ai/model?slug=healthgpt-pro-4b · How It Works · Data refreshed daily, snapshot 2026-11-16.