TAF-MED Benchmark

What is TAF-MED?

TAF-MED is a physician-reviewed benchmark of 500 fixed three-turn medical safety scenarios, evaluating LLM responses for unsafe guidance across multi-turn…

Released

2026-08-10

Evaluates

Biology & Drug Discovery, Safety, Safety & Trustworthiness

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.10258

TAF-MED paper

• Paper https://arxiv.org/abs/2608.10258

Which sources cite TAF-MED?

• TAF-MED

Related Biology & Drug Discovery, Safety, Safety & Trustworthiness benchmarks

• A Large-Scale Dataset and Benchmark
• ABC-Bench
• ActBench
• Agent Planning Benchmark
• AgentHarm
• AgentHazard
• AgentS4D
• AICompanionBench