StanceBench

What is StanceBench?

StanceBench evaluates interpersonal stance in conversational speech across 9 dimensions using LLM-as-a-judge on the Seamless Interaction corpus.

Released

2026-06-27

Evaluates

General AI, Speech & Audio, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.22658

StanceBench paper

• Paper https://arxiv.org/abs/2607.22658

Which sources cite StanceBench?

• StanceBench

Related General AI, Speech & Audio, cs.AI benchmarks

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