Fetch, scrape and extraction
No independent board scores fetch on its own. The closest is openbenchmarks' coding-agent board, where an agent searches and then fetches pages to finish 100 held-out documentation tickets, with the model and budgets fixed. Read it as search and fetch together.
Independent benchmarkopenbenchmarks.com, web-search-for-coding-agents · snapshot Sep 15, 2026
Coding tickets completed, search and fetch
Mean of 3 runs; tokens are the agent's context per ticket. The board says to re-read the live page before quoting.
Tools
Alphabetical. Links go to each vendor's own site.
| Tool | What it does | Evidence | Price or terms |
|---|---|---|---|
| Bright Data | proxy network and scraping browser | none yet | plans by volume; browser render and CAPTCHA solving included |
| Exa Contents | clean page text for URLs | 83.0% with Exa deep search (search + fetch) | $1/1k |
| Firecrawl | URL to markdown; crawl and extract | 76.0% (search + fetch) | 1,000 credits/mo free; keyless tier |
| Jina Reader | URL to markdown by prefixing r.jina.ai | none yet | free without a key at 20 requests/min |
| Kagi Extract | page content extraction API | none yet | $4/1k |
| Oxylabs | proxy network and scraper APIs | none yet | plans by volume |
| Parallel Extract | page content extraction API | 77.0% with Parallel advanced search (search + fetch) | $1/1k |
| ScrapingBee | scraping API with headless browsers | none yet | plans by volume |
| Tavily Extract | page content extraction API | 60.0% with Tavily advanced search (search + fetch) | ~$1.60/1k |
| TinyFish Fetch | search and fetch, free | 79.0% (search + fetch) | free |
| You.com Contents | page content extraction API | none yet | $1/1k |
| ZenRows | scraping API with anti-bot bypass | none yet | plans by volume |
Caveats
- On the same site's search-only board the order changes: Perplexity leads at 77.3% and Firecrawl is second at 70.3%. Whether the agent may fetch pages decides the winner.