Skip to content

Benchmark

Tau2 Airline

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

Models measured
20
Scores recorded
20
Sources
1
IQ weight
1.44

Score distribution

60.1%
Mean
60.5%
Median
9.2%
Std dev
45.5%
10th percentile
67.5%
90th percentile
44%
Min
44%78%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.44 for chat models, measured over 20 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78%
2LongCat-Flash-Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.5%
3GPT 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67%
4GPT-5.1-Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67%
5Ember-1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66%
6Nova 2 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.8%
7OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.8%
8Claude Haiku 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.6%
9GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.6%
10Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.5%
11LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58%
12longcat-flash-lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58%
13Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58%
14Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.5%
15Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.3%
16Mercury 2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53%
17Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48%
18GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim45.5%
19Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim45.5%
20Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim44%

Data credits: Data by LLM Stats