Skip to content

Benchmark

AutomationBench-AA

Scores are percentages.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.18

Score distribution

48.4%
Mean
45.4%
Median
11.9%
Std dev
39.1%
10th percentile
73.3%
90th percentile
39.1%
Min
39.1%73.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.18 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.3%
2Grok 4.5· LLM Stats data51.4%
3Muse Wonder Full· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim45.4%
4Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim41.8%
5Muse Wonder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim39.1%
6Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim39.1%

Data credits: Data by LLM Stats