Tau2 Average: leaderboard
TAU2 aggregate over retail, telecom, and airline conversational-agent domains, testing policy following, tool use, and user-goal completion.
Metric: Success Rate (%). Source: arxiv.org. Source: benchmarklist.com. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B | 76.9 | #200 |
| 2 | Gemma 4 26B A4B | 68.2 | #358 |
| 3 | Gemma 4 E4B | 42.2 | #767 |
| 4 | Gemma 4 E2B | 24.5 | #1070 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=tau2-average · How It Works · Data refreshed daily, snapshot 2026-10-20.