Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Python ai-agentsai-toolsbrowser-agentbrowser-automationbrowser-usecdpcloud-browsercomputer-useheadless-browserllmmcpplaywrightpythonremote-browserstealth-browserweb-automationweb-scraping
improve readme plot styling
Alezander99919f2eee6b5
diff --git a/README.md b/README.mdindex 4ba526918..61412a638 100644--- a/README.md+++ b/README.md@@ -95,9 +95,9 @@ Check out the [library docs](https://docs.browser-use.com/open-source/introducti# Open Source vs Cloud<picture>- <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/browser-use/benchmark/main/official_plots/accuracy_by_model_light.png">- <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/browser-use/benchmark/main/official_plots/accuracy_by_model_dark.png">- <img alt="BU Bench V1 - LLM Success Rates" src="https://raw.githubusercontent.com/browser-use/benchmark/main/official_plots/accuracy_by_model_light.png" width="100%">+ <source media="(prefers-color-scheme: light)" srcset="static/accuracy_by_model_light.png">+ <source media="(prefers-color-scheme: dark)" srcset="static/accuracy_by_model_dark.png">+ <img alt="BU Bench V1 - LLM Success Rates" src="static/accuracy_by_model_light.png" width="100%"></picture>We benchmark Browser Use across 100 real-world browser tasks. Full benchmark is open source: **[browser-use/benchmark](https://github.com/browser-use/benchmark)**.diff --git a/static/accuracy_by_model_dark.png b/static/accuracy_by_model_dark.pngnew file mode 100644index 000000000..fe8797481Binary files /dev/null and b/static/accuracy_by_model_dark.png differdiff --git a/static/accuracy_by_model_light.png b/static/accuracy_by_model_light.pngnew file mode 100644index 000000000..a6bc852f9Binary files /dev/null and b/static/accuracy_by_model_light.png differ