Browserbase for AI agents: benchmark results
Browserbase (browser infrastructure) was tested on scrape and search, not on map and crawl. It got the same tasks, the same model (Claude Haiku 5.5), the same prompt and the same limits as every other provider, and a script checked every answer. Browserbase here means its HTTP Fetch and Search APIs, not its browser sessions.
Scrape 60 tasks · Read one page and pull out exact fields: prices, versions, install commands.
- Tasks done
- 82%
- 49 of 60
- 95% interval
- 78%–100%
- Cost per finished task
- 1.12¢
- Median time
- 3.3 s
7th of 8 on tasks done. Browserbase is behind Context.dev (92%), but the gap of 10 points is too small to rule out chance.
Raw output, no model: the API's own response held every answer on 37 of 55 applicable tasks (67%), at 0.65¢ of API spend per finished task.
| Provider | Tasks done | 95% interval | Cost per finished task | Median time |
|---|---|---|---|---|
| Context.dev | 55 of 60 (92%) | 90%–100% | 0.72¢ | 3.7 s |
| Linkup | 54 of 60 (90%) | 90%–90% | 0.60¢ | 3.4 s |
| Firecrawl | 54 of 60 (90%) | 90%–90% | 1.22¢ | 3.3 s |
| TinyFish | 54 of 60 (90%) | 80%–92% | 0.43¢ | 3.5 s |
| Scrapfly | 53 of 60 (88%) | 80%–90% | 0.61¢ | 5.0 s |
| Jina | 52 of 60 (87%) | 60%–92% | 0.57¢ | 3.8 s |
| Browserbase | 49 of 60 (82%) | 78%–100% | 1.12¢ | 3.3 s |
| Spider | 12 of 60 (20%) | 4%–100% | 2.48¢ | 4.6 s |
Search 60 tasks · Find a fact on the live web: a package's latest version, a filing figure, a release date.
- Tasks done
- 38%
- 23 of 60
- 95% interval
- 21%–59%
- Cost per finished task
- 5.97¢
- Median time
- 12 s
5th of 5 on tasks done. Browserbase finished 47 points fewer tasks than Firecrawl, the leader. That gap is big enough to rule out chance.
Raw output, no model: the API's own response held every answer on 1 of 53 applicable tasks (2%), at 30.0¢ of API spend per finished task.
| Provider | Tasks done | 95% interval | Cost per finished task | Median time |
|---|---|---|---|---|
| Firecrawl | 51 of 60 (85%) | 69%–100% | 3.04¢ | 11 s |
| Linkup | 50 of 60 (83%) | 65%–97% | 2.55¢ | 5.3 s |
| Context.dev | 45 of 60 (75%) | 52%–96% | 1.82¢ | 5.2 s |
| TinyFish | 44 of 60 (73%) | 47%–96% | 1.31¢ | 5.3 s |
| Browserbase | 23 of 60 (38%) | 21%–59% | 5.97¢ | 12 s |
Read these numbers with
- Its Search responses carried useful URLs and titles but blank snippets, which limits how many facts the model could answer from them.
Browserbase compared
- Firecrawl vs Browserbase scrape and search, compared with Firecrawl
- TinyFish vs Browserbase scrape and search, compared with TinyFish