Updated daily at 05:00 UTC
Benchmark
Artificial Analysis Speech Agent Arena
Measures: People hold blind live voice conversations with two speech-to-speech models across 35 scenarios (15 with tools, such as booking a dental appointment or ordering takeout) and pick the one they prefer; ranked by Bradley-Terry Elo, with the % of correct final tool calls alongside.
- Maintainer
- Artificial Analysis
- Introduced
- —
- Status
- Active
- Saturation
- Headroom
- Typical provenance
- Independent
- In scoring set
- Yes
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results