Jina Reader for AI agents: benchmark results
Jina (content API) was tested on scrape, not on search, 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. Jina here means Jina Reader (r.jina.ai), scored on scrape only. An earlier 7-task Jina Search run is kept as historical evidence and isn't part of these scores.
Scrape 60 tasks · Read one page and pull out exact fields: prices, versions, install commands.
- Tasks done
- 87%
- 52 of 60
- 95% interval
- 60%–92%
- Cost per finished task
- 0.57¢
- Median time
- 3.8 s
6th of 8 on tasks done. Jina is behind Context.dev (92%), but the gap of 5 points is too small to rule out chance.
Raw output, no model: the API's own response held every answer on 51 of 55 applicable tasks (93%), at 0.01¢ of API spend per finished task.
Tuned settings, frozen before the run: 52 of 60 (87%), against 87% with defaults.
| 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 |
Jina compared
- Firecrawl vs Jina scrape, compared with Firecrawl
- Context.dev vs Jina scrape, compared with Context.dev
- Jina vs Scrapfly scrape, compared with Scrapfly