MTVA-Bench

What is MTVA-Bench?

A benchmark for evaluating language models within cascaded voice agents across multi-turn interactions. Benchmark Radar tracks MTVA-Bench, cited by 1 source…

Released

2026-09-17

Evaluates

Agents, General AI, Speech & Audio

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.20152

MTVA-Bench paper

• Paper https://arxiv.org/abs/2609.20152

Which sources cite MTVA-Bench?

• MTVA-Bench

Related Agents, General AI, Speech & Audio benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench
• ABACUS