AA Speech to Speech - Tau-Voice 2.0: leaderboard

Sierra tau-bench v2.0.0 voice: 50 English tasks each in airline, retail and telecom; three trials; GPT5.5 low simulated caller speaking ElevenLabs eleven_v3; common prompt/tools/policy, 2400-second call limit. State/action/output checks; infrastructure errors excluded and rerun. Overall is equal domain mean. GPT-Live's source-declared backend prompt differs. Separate from V1; no cross-edition score replacement. Metric: Pass@1 (%), mean of three trials. Source: https://artificialanalysis.ai/speech-to-speech

Metric: Pass@1 (%), mean of three trials. Source: artificialanalysis.ai. Saturation forecast: Rough model projection: around 2026. 11 models tracked. Updated 17 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Phonic 1High85.56
2GPT-Live 1 (Astra, medium)80.44
3GPT-Live 1 (Sol, low)74.67
4Grok Voice 3.066.89
5Gemini 3.8 Live (Extended Thinking)High65.11
6Qwen Audio 3.0 Realtime Plus59.78
7Eleven Realtime v1 Max57.78
8Eleven Realtime v1 Mini53.78
9GPT Realtime 2.1High35.78
10Gemini 3.8 Live35.56
11Gemini 3.1 Flash Live High31.78

Interactive version: theaggregate.ai/benchmark?slug=aa-speech-to-speech-tau-voice-2-0 · How It Works · Data refreshed daily, snapshot 2026-11-17.