Skip to content

Benchmark

TAU-bench Airline

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

Models measured
23
Scores recorded
23
Sources
1
IQ weight
1.66

Score distribution

49.5%
Mean
50%
Median
13.1%
Std dev
32.4%
10th percentile
60.8%
90th percentile
14%
Min
14%70%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.66 for chat models, measured over 23 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. claim70%
2MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.62%
3GLM 4.5 Air· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.8%
4GLM 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.4%
5Claude Sonnet 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60%
6MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.60%
7Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60%
8Claude Opus 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.6%
9Claude Sonnet 3.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.4%
10Claude Opus 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56%
11GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50%
12o1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50%
13GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.4%
14o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.2%
15Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49%
16Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46%
17Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46%
18Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim44%
19GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.8%
20GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim36%
21o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim32.4%
22Claude Haiku 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim22.8%
23GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim14%

Data credits: Data by LLM Stats