Skip to content

Benchmark

OSWorld Extended

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

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

22%
Mean
22%
Median
0%
Std dev
22%
10th percentile
22%
90th percentile
22%
Min

Leaderboard

#ModelScore
1Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim22%

Data credits: Data by LLM Stats