Skip to content

Benchmark

Tau2 Retail

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

Models measured
22
Scores recorded
22
Sources
1
IQ weight
1.87

Score distribution

75.9%
Mean
76.5%
Median
10%
Std dev
62.8%
10th percentile
88.9%
90th percentile
56.9%
Min
56.9%91.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.87 for chat models, measured over 22 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 Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.9%
2Claude Sonnet 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.7%
3Claude Opus 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.9%
4LongCat-Flash-Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.6%
5Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.1%
6Claude Haiku 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.2%
7GPT 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82%
8GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.1%
9OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.2%
10GPT 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.9%
11GPT-5.1-Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.9%
12Nova 2 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.5%
13longcat-flash-lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.1%
14Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.9%
15Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.3%
16LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.3%
17Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.6%
18Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.8%
19GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.4%
20Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.8%
21Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.3%
22Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.9%

Data credits: Data by LLM Stats