# τ²-bench (retail) — AI model rankings

task success in the retail domain of the second-generation customer-service evaluation

7 tracked models have a published τ²-bench (retail) score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Gemini 3.1 Pro | Google | 90.8% | Lab | Feb 19 2026 |
| 2 | Gemini 3.0 Pro | Google | 85.3% | Lab | Nov 18 2025 |
| 3 | GPT-5.2 | OpenAI | 82% | Lab | Dec 11 2025 |
| 4 | GPT-5 | OpenAI | 81.1% | Lab | Aug 7 2025 |
| 5 | GPT-5 mini | OpenAI | 78.3% | Lab | Aug 7 2025 |
| 6 | GPT-5.1 | OpenAI | 77.9% | Lab | Nov 12 2025 |
| 7 | GPT-5 nano | OpenAI | 62.3% | Lab | Aug 7 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/tau2-retail
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.