OpenSafeIntent Benchmark

What is OpenSafeIntent?

OpenSafeIntent is a benchmark of controlled prompt-sets that vary user intent while holding the underlying task fixed. Each datapoint contains benign…

Released

2026-07-02

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.02047

OpenSafeIntent paper

• Paper https://arxiv.org/abs/2607.02047

Which sources cite OpenSafeIntent?

• OpenSafeIntent

Related General AI, Language & Knowledge, cs.CL 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