Skip to content

Benchmark

TAU-bench Retail

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.

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
22.6%86.2%
The band covers the middle 80% of scores. The line marks the median.

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

#ModelScore
1Claude Sonnet 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.2%
2Claude Opus 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.4%
3Claude Opus 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.4%
4Claude Sonnet 3.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.2%
5Claude Sonnet 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.5%
6GLM 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.7%
7GLM 4.5 Air· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.9%
8Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.5%
9o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.8%
10o1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.8%
11Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.6%
12Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.2%
13GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.4%
14GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68%
15GPT OSS 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.8%
16MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.67.8%
17Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.8%
18MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.63.5%
19Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.9%
20GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.3%
21o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.6%
22GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.8%
23GPT OSS 20b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.8%
24Claude Haiku 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51%
25GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim22.6%

Data credits: Data by LLM Stats