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

Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.