OpenRouter launches real-time web search benchmark: how to choose engine, depth and model for agents
Original title:Live Web Search Benchmarks: Pick the Right Engine, Depth, and Model for Your Agent
AI summary
OpenRouter released a real-time leaderboard that systematically evaluates combinations of four configuration types: model, search engine, search method and budget. Data shows that increasing the search budget from 1 round to 25 rounds nearly doubles the BrowseComp score, while cost rises only 2.5-7x; model choice matters more than engine, with an average score gap of 15 points vs 10 points. For tasks with high failure rates, search depth should be reduced to control costs.
Key Takeaways
- OpenRouter released a real-time leaderboard that systematically evaluates combinations of four…
- Data shows that increasing the search budget from 1 round to 25 rounds nearly doubles the…
- model choice matters more than engine,with an average score gap of 15 points vs 10 points.
- For tasks with high failure rates,search depth should be reduced to control costs.
Quick Facts
- Published
- Updated
- Category
- Products & Apps
- AI score
- 67
这份基准把搜索预算的作用量化到分数与成本上,显示从单轮增加到 25 轮搜索,质量提升幅度超过更换模型或引擎,为 agent 搜索配置提供了更直接的取舍依据。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: OpenRouter launches real-time web search benchmark: how to choose engine, depth and model for agents. August 12, 2026. https://new.nat6.net/en/news/cmsq9h6gs01x5ronde8fdla7e/