Claude agents and computer use: charts and benchmarks
Every chart we tracked that shows Claude agents and computer use, from the lab itself and from the trackers people trust, with how far each one travelled.
Official charts from Anthropic
As published on X, Hugging Face, GitHub and their blog. Each card opens our own page for the chart.
More charts that feature Claude agents and computer use
Benchmark trackers, other labs and researchers. Each card opens our own page for the chart.
Make it yours
Your numbers, in this benchmark bar chart.
Starts from the real numbers of "Where a researcher went wrong, could Claude have done better?" by Anthropic. Replace every number with yours before you post. Make one like this, step by step
Free pictures carry a small "Made with ViralChart" line. That line is how other people find us.
Questions people ask
What charts show Claude agents and computer use?
We hold 13 charts that show Claude agents and computer use, 6 of them published by Anthropic. The newest is "Claude Haiku 5.5 benchmark comparison" (Oct 7, 2026). Each card opens our own page for the chart.
Who publishes Claude agents and computer use benchmark charts?
Anthropic, @OpenAI, @AIatMeta, @OpenAIDevs, @Kimi_Moonshot, deepmind.google