PreAct-Bench

What is PreAct-Bench?

PreActBench is a benchmark for predictive monitoring in LLMs, consisting of 1,000 paired ethical and unethical action trajectories across five domains. It…

Released

2026-06-03

Evaluates

General AI, Language & Knowledge, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.09890

PreAct-Bench paper

• Paper https://arxiv.org/abs/2606.09890

Which sources cite PreAct-Bench?

• PreAct-Bench

Related General AI, Language & Knowledge, cs.LG benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench