RedVox Benchmark

What is RedVox?

RedVox is a multilingual safety and fairness benchmark for speech models, built on real voices. It covers unsafe and unfair stereotypical requests across five…

Released

2026-06-25

Evaluates

General AI, Safety, Safety & Trustworthiness

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.26968

RedVox paper

• Paper https://arxiv.org/abs/2606.26968

Which sources cite RedVox?

• RedVox

Related General AI, 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