DTap-Bench (Benign Tasks) - Medical: leaderboard

Metric: Benign task success rate (%; 642 benign medical service tasks, no attack applied; a task succeeds when a rule-based check of the final environment state finds the instruction fully completed; mean of its task-category rates). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1GPT-5.486.1
2Gemini 3 Pro81.9
3GPT-5.266.3
4GPT-5.152.8
5GPT-OSS-120B35.8

Interactive version: theaggregate.ai/benchmark?slug=dtap-bench-benign-tasks-medical · How It Works · Data refreshed daily, snapshot 2026-09-26.