DTap-Bench (Indirect Attacks) - Medical: leaderboard

Metric: Attack success rate (%; 222 indirect red-teaming medical service tasks: third-party tool, skill and environment injections into a benign user task; an attack succeeds when a rule-based check of the final environment state finds the malicious goal fully achieved; fixed attack sequences that DTap-Red optimized on a surrogate agent; mean of its risk-category rates). Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked.

Top models

#ModelScore
1GPT-5.437.5
2GPT-5.247.2
3Gemini 3 Pro49.1
4GPT-OSS-120B62.1

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