Benchmark
tau2-bench v0.1 retail pass^2
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 6
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- 0.82
Score distribution
- 64%
- Mean
- 66.8%
- Median
- 7%
- Std dev
- 58.7%
- 10th percentile
- 69.4%
- 90th percentile
- 49.8%
- Min
This benchmark has a weight of 0.82 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 5submission-gpt-5_sierra_2025-08-09, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs | 71.8% |
| 2 | Qwen3 Maxsubmission-qwen3-max_qwen_2026-01-23, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs | 69.4% |
| 3 | Qwen3 Maxsubmission-qwen3-max_qwen_2024_09_23· Sierra tau-bench Leaderboard data docs | 67.5% |
| 4 | Claude Sonnet 3.7submission-claude-3-7-sonnet_anthropic_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs | 66.8% |
| 5 | GPT 4.1submission-gpt-4-1_openai_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs | 64.2% |
| 6 | o4 Minisubmission-o4-mini_openai_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs | 58.7% |
| 7 | GPT-4.1 minisubmission-gpt-4-1-mini_openai_2024-06-20, usersim-gpt-4.1-2025-04-14· Sierra tau-bench Leaderboard data docs | 49.8% |
Data credits: Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence)