SafeRun Benchmark

What is SafeRun?

A benchmark for evaluating language-model running plans under physiological, safety, and instruction-following constraints.

Released

2026-06-08

Evaluates

General AI, Planning, Safety, Safety & Trustworthiness

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.09027

SafeRun paper and dataset

• Paper https://arxiv.org/abs/2606.09027
• Dataset https://huggingface.co/datasets/zzp-seeker/SafeRun-RunPlanning-Benchmark

Which sources cite SafeRun?

• SafeRun

Related General AI, Planning, Safety, Safety & Trustworthiness benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision