Tau3-Voice Multilingual Airline: leaderboard
Sierra's τ³-Voice leaderboard (taubench.com), Multilingual edition (τ³-Voice 2.0, the site's default view): voice agents handle τ³-bench customer-service calls with a simulated customer in six languages. Standard submissions only; incomplete submission packages are not shown. Airline domain. Score: task-completion pass@1 (%), the six languages weighted equally. Higher is better.
Metric: Task completion pass@1 (%), six languages weighted equally. Source: taubench.com. Saturation forecast: Rough model projection: around 2026. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ava Zero | 83.67 | |
| 2 | gpt-live-1 | 83.33 | |
| 3 | Phonic 1 (High) | 81.67 | |
| 4 | Grok Voice 2.0 (High) | 63.88 | |
| 5 | Gemini 3.8 Live (Extended Thinking) | 62.52 |
Interactive version: theaggregate.ai/benchmark?slug=tau3-voice-multilingual-airline · How It Works · Data refreshed daily, snapshot 2026-11-05.