BROWSER USE

- Browser Use Agents: give Browser Use a task and receive completed work. API V4 is current for new integrations.
- Browser Infrastructure: connect your agent or automation to managed browsers through SDK, REST, or CDP. Starts at $0.02/browser-hour.
- Developer tools: Open Source, Browser Harness, SDK, and MCP support the two products above.

[Developer Index](https://browser-use.com/index.md)
[Product Map](https://browser-use.com/llms.txt)
[Full Product Context](https://browser-use.com/llms-full.txt)
[Pricing](https://browser-use.com/pricing.md)
[Cloud Docs](https://docs.browser-use.com/cloud/quickstart)
[Open Source Docs](https://docs.browser-use.com/open-source/introduction)

---

# Cloud Browser Benchmarks

# Browser benchmarks.

Every protected site we try, against every provider, changing nothing but the browser.

[Agents](https://browser-use.com/benchmarks/agents)[Browsers](https://browser-use.com/benchmarks/browsers)

BrowserBenchBU Stealth Benchmark

### BrowserBench

Browser Use Cloud: 84.8% of tasks solved. 8.4 points ahead of Hyperbrowser, the next best.

84.8%

76.4%

76%

73.3%

70.3%

Browser Use Cloud

Hyperbrowser

Anchor

Steel

Browserbase

ProviderSuccess Rate

Browser Use Cloud84.8%

Hyperbrowser76.4%

Anchor76%

Steel73.3%

Browserbase70.3%

BrowserBench · updated 2026-03-21 · [all benchmarks](https://browser-use.com/benchmarks/agents)

What it measures

[BrowserBench](https://github.com/Halluminate/browserbench) is a third-party benchmark from Halluminate. 296 tasks across antibot-protected sites. Includes lower-security sites, so scores are generally higher than our stealth benchmark.

How it was run

-   Benchmark: Created by Halluminate. We ran it ourselves across all providers.
-   Tasks: 296 tasks across antibot-protected websites.
-   Scoring: Pass/fail based on whether the agent was blocked by antibot protection.