SPEARBench

What is SPEARBench?

SPEARBench evaluates naturalness in streaming speech-to-speech language models via question-answer interactions, measuring latency, interruptions, speech…

Released

2026-07-06

Evaluates

General AI, Speech & Audio, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.05365

SPEARBench paper

• Paper https://arxiv.org/abs/2607.05365
• Website https://thomasthebaud.github.io/SPEAR-benchmark-website/#welcome

Which sources cite SPEARBench?

• SPEARBench

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

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