AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Tau2 Retail
τ²-bench retail domain evaluates conversational AI agents in customer service scenarios within a dual-control environment where both agent and user can interact with tools. Tests tool-agent-user interaction, rule adherence, and task consistency in retail customer support contexts.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Sierra
- Benchmark release
- 2025-06-09
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 26
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Claude Opus 4.6 | 0.919 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| Claude Sonnet 4.6 | 0.917 | Not recorded | Not recorded | 2026-02-17 · model_announcement | LLM Stats |
| Claude Opus 4.5 | 0.889 | Not recorded | Not recorded | 2025-11-24 · model_announcement | LLM Stats |
| LongCat-Flash-Thinking-2601 | 0.886 | Not recorded | Not recorded | 2026-01-14 · model_announcement | LLM Stats |
| Claude Haiku 4.5 | 0.832 | Not recorded | Not recorded | 2025-10-15 · model_announcement | LLM Stats |
| GPT-5.2 | 0.82 | Not recorded | Not recorded | 2025-12-11 · model_announcement | LLM Stats |
| GPT-5 | 0.811 | Not recorded | Not recorded | 2025-08-07 · model_announcement | LLM Stats |
| o3 | 0.802 | Not recorded | Not recorded | 2025-04-16 · model_announcement | LLM Stats |
| Nova 2 Omni | 0.783 | Not recorded | Not recorded | 2025-12-02 · model_announcement | LLM Stats |
| GPT-5.1 | 0.779 | Not recorded | Not recorded | 2025-11-13 · model_announcement | LLM Stats |
| GPT-5.1 Instant | 0.779 | Not recorded | Not recorded | 2025-11-12 · model_announcement | LLM Stats |
| GPT-5.1 Thinking | 0.779 | Not recorded | Not recorded | 2025-11-12 · model_announcement | LLM Stats |
| Nova 2 Pro | 0.777 | Not recorded | Not recorded | 2025-12-02 · model_announcement | LLM Stats |
| Nova 2 Lite | 0.765 | Not recorded | Not recorded | 2025-12-02 · model_announcement | LLM Stats |
| LongCat-Flash-Lite | 0.731 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| Qwen3-235B-A22B-Thinking-2507 | 0.719 | Not recorded | Not recorded | 2025-07-25 · model_announcement | LLM Stats |
| LongCat-Flash-Thinking | 0.715 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3-235B-A22B-Instruct-2507 | 0.713 | Not recorded | Not recorded | 2025-07-22 · model_announcement | LLM Stats |
| LongCat-Flash-Chat | 0.7127 | Not recorded | Not recorded | 2025-08-29 · model_announcement | LLM Stats |
| Kimi K2-Instruct-0905 | 0.706 | Not recorded | Not recorded | 2025-09-05 · model_announcement | LLM Stats |
| Kimi K2 Instruct | 0.706 | Not recorded | Not recorded | 2025-07-11 · model_announcement | LLM Stats |
| Qwen3-Next-80B-A3B-Thinking | 0.678 | Not recorded | Not recorded | 2025-09-10 · model_announcement | LLM Stats |
| GPT-4o | 0.634 | Not recorded | Not recorded | 2024-08-06 · model_announcement | LLM Stats |
| Nemotron 3 Super (120B A12B) | 0.6283 | Not recorded | Not recorded | 2026-03-11 · model_announcement | LLM Stats |
| Qwen3-Next-80B-A3B-Instruct | 0.573 | Not recorded | Not recorded | 2025-09-10 · model_announcement | LLM Stats |
| Nemotron 3 Nano (30B A3B) | 0.569 | Not recorded | Not recorded | 2025-12-15 · model_announcement | LLM Stats |