---
title: "Avg search time (search only): Web Search for Coding Agents Benchmark | Openbenchmarks"
description: "Independent benchmarks for build-vs-buy decisions. Verifiable, reproducible and open source."
url: https://openbenchmarks.com
---

[](https://openbenchmarks.com/) 

[← full benchmark](https://openbenchmarks.com/web-search-for-coding-agents) 

[benchmarks](https://openbenchmarks.com/) / [web search for coding agents](https://openbenchmarks.com/web-search-for-coding-agents) / avg search time · search only 

 last run 15 Sept 2026

# Average search time: Web Search for Coding Agents, search only 

\[01\] result

Parallel turbo searches fastest at 333 ms 

Of the 14 web search API configurations tested in search-only mode on the Web Search for Coding Agents Benchmark, Parallel turbo had the fastest average search time: 333 ms, pooled across all three runs of the 100-ticket set.

\[02\] the benchmark

A coding agent patches a small `httpx` client against the vendor's current official API documentation on 100 held-out enterprise SaaS tickets, using each vendor's web search API. A ticket passes only when the patch compiles and every ground-truth token is grounded in a URL the search returned. Only the search API changes between rows.

\[03\] how average search time is measured

Average search time is the mean latency of each web\_search tool call, pooled across all three runs. Lower is better.

[open code Harness, scoring and vendor runners are public in openbenchmarks-labs/web-search-for-coding-agents. github → ](https://github.com/openbenchmarks-labs/web-search-for-coding-agents) 

\[04\] search only

Ranking, sorted by average search time

The agent has web\_search only: it reads titles, URLs and snippets, and cannot open a page.

benchmarks/coding-agents/search-only/avg-search-time complete 

Top 8 

__Every configuration, ranked by average search time__
| Rank | Vendor | Endpoint & configuration | Avg search time |
| --- | --- | --- | --- |
| 1 | [Parallel turbo](https://parallel.ai "Open Parallel turbo in a new tab") | POST /v1/search mode=turbo | 333ms |
| 2 | [Exa instant](https://exa.ai "Open Exa instant in a new tab") | POST /search type=instant | 447ms |
| 3 | [Brave](https://brave.com/search/api/ "Open Brave in a new tab") | POST /res/v1/llm/context | 523ms |
| 4 | [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights | 596ms |
| 5 | [Exa fast](https://exa.ai "Open Exa fast in a new tab") | POST /search type=fast | 626ms |
| 6 | [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights · knowledge=core | 677ms |
| 7 | [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=standard · full\_content=false · focus=general | 878ms |
| 8 | [Parallel fast](https://parallel.ai "Open Parallel fast in a new tab") | POST /v1/search mode=fast | 953ms |
| 9 | [Perplexity](https://www.perplexity.ai "Open Perplexity in a new tab") | POST /search search\_context\_size=low | 957ms |
| 10 | [Linkup fast](https://www.linkup.so "Open Linkup fast in a new tab") | POST /v1/search depth=fast | 1.39s |
| 11 | [Tavily basic](https://tavily.com "Open Tavily basic in a new tab") | POST /search search\_depth=basic | 1.72s |
| 12 | [TinyFish](https://www.tinyfish.ai "Open TinyFish in a new tab") | GET api.search.tinyfish.ai | 2.15s |
| 13 | [Firecrawl](https://firecrawl.dev "Open Firecrawl in a new tab") | POST /v2/search | 2.87s |
| 14 | [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=lite · full\_content=false · focus=general | 3.15s |

Openbenchmarks [← web search for coding agents](https://openbenchmarks.com/web-search-for-coding-agents) © 2026 Openbenchmarks