Benchmark
TAU-bench Retail
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.
All agentic benchmarksScores from LLM Stats data.
- Models measured
- 25
- Scores recorded
- 25
- Sources
- 1
- IQ weight
- 2.03
Score distribution
- 67.8%
- Mean
- 68.4%
- Median
- 13.1%
- Std dev
- 54.8%
- 10th percentile
- 81.4%
- 90th percentile
- 22.6%
- Min
This benchmark has a weight of 2.03 for chat models, measured over 25 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 | Claude Sonnet 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.2% |
| 2 | Claude Opus 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.4% |
| 3 | Claude Opus 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.4% |
| 4 | Claude Sonnet 3.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.2% |
| 5 | Claude Sonnet 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.5% |
| 6 | GLM 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 79.7% |
| 7 | GLM 4.5 Air· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.9% |
| 8 | Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.5% |
| 9 | o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.8% |
| 10 | o1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.8% |
| 11 | Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.6% |
| 12 | Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.2% |
| 13 | GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.4% |
| 14 | GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68% |
| 15 | GPT OSS 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.8% |
| 16 | MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 67.8% |
| 17 | Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.8% |
| 18 | MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 63.5% |
| 19 | Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 60.9% |
| 20 | GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 60.3% |
| 21 | o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.6% |
| 22 | GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 55.8% |
| 23 | GPT OSS 20b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.8% |
| 24 | Claude Haiku 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51% |
| 25 | GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 22.6% |
Data credits: Data by LLM Stats