# Browser Use Codex API Evaluation

**Category:** Browser
**Score:** 81 (B)

This is the agent-readable Devtool Arena evaluation page for Browser Use on Codex API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 81 |
| Grade | B |
| Eval score | 73 |
| Discovery score | 100 |
| Cost | $0.27 |
| Runtime | 1m 18s |
| Tool calls | 23 |
| Errors | 9 |
| Tokens used | 384972 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | https://context7.com/browser-use/browser-use |
| llms.txt | https://browser-use.com/llms.txt |
| MCP server | https://github.com/browser-use/browser-use/blob/main/server.json |
| Typed SDK | https://registry.npmjs.org/browser-use-sdk |
| OpenAPI | https://docs.browser-use.com/cloud/openapi/v4.json |
| Agent skills | https://github.com/browser-use/browser-use/blob/main/skills/browser-use/SKILL.md |
| CLI | https://docs.browser-use.com/open-source/quickstart |

## Evaluation Prompt

````text

# Task
Using https://docs.browser-use.com, complete the following task:

Using Browser Use, build me a Python script that:

1. Install the Browser Use Python package
2. Open a browser session
3. Navigate to "https://example.com"
4. Extract the page title and the main heading (h1) text
5. Take a screenshot and save as "screenshot.png" (if supported)
6. Close the session
7. Print results as JSON: {"url": "...", "title": "...", "heading_text": "...", "screenshot_saved": true/false}

Use the official Browser Use Python library — not raw HTTP calls. 

## Execution
After creating the script, run it to verify it works:
```bash
cd /home/daytona/app && python <your_script>.py
```

The script should print output to stdout. If there are errors, debug and fix them until it runs successfully.

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Cost | Yes | 0 | 0 | $0.27 ($0.20–0.40, good) |
| Time | Yes | 0 | 1 | 78s (1–2min, great) |
| Efficiency | Yes | 0 | 0 | 23 tool calls (≤25, below average) |
| Found Docs | Yes | 0 | — | Touched docs at docs.browser-use.com: yes (17 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 9 |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 2 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 27 |
| Tool call traces | 23 |
| Generated files | 2 |
| Exit code | 0 |
| Completed at | 2026-09-29T16:18:04.740086+00:00 |

### Generated Files

- /home/daytona/app/requirements.txt
- /home/daytona/app/browser_example.py

## Related Pages

- [Codex API leaderboard](/leaderboard/codex/api)
- [Compare Codex API companies](/leaderboard/codex/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/codex/api/browser-use