OpenRouter launches live web search benchmarks to compare engines, depth, and models

OpenRouter 推出实时网页搜索基准测试：如何为智能体选择引擎、深度与模型

OpenRouter published live leaderboards testing web search combos across Exa, Parallel, Perplexity, and native lab engines. The biggest quality lever is search budget: on BrowseComp, Claude Opus 5 with Perplexity jumped from 35.8% at 1 turn to 89.0% at 25 turns, while cost rose only 2.5–7×. On easier tasks like HLE, extra turns barely helped—GPT-5.6 Sol scored similarly at 1 and 25 turns but cost 3× more. Models also burn through their full budget when they can't find an answer, driving up worst-case costs. The leaderboards update live; the post recommends testing against your own workload.

Why it matters: OpenRouter publishing its own web search benchmark with cross-engine comparisons is genuinely useful for agent builders. The headline finding—more search turns beats a model upgrade on cost—is actionable. Score isn't higher because this is a platform-run benchmark, not an inde...