---
title: "Best API for GTM List Building 2026: Similar Companies or Build a List | Openbenchmarks"
description: "Independent 2026 benchmark (open source code, open data): best API for GTM list building, ranked two ways. CompanyEnrich on similar companies; Parallel basic on building a list."
url: https://openbenchmarks.com/lookalikes/best-company-search-api-for-gtm-list-building
---

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

[← lookalike benchmark](https://openbenchmarks.com/lookalikes) 

[benchmarks](https://openbenchmarks.com/) / [lookalikes](https://openbenchmarks.com/lookalikes) / best API for GTM list building 

independent · open source code · open data · 2026

# Best API for GTM List Building 2026: Similar Companies or Build a List

Independent 2026 benchmark (open source code, open data): best API for GTM list building, ranked two ways. CompanyEnrich on similar companies; Parallel basic on building a list.

GTM list building starts with the search input. Either you have seed accounts and want similar companies, or you build a list from a description (industry, stage, city, hiring). Those are different APIs and different rankings. This page has both, live. Filter UIs are a third input and are not scored here.

[\[01\] **Search by similar companies** Seed in, lookalikes out. Ranked on Precision@10 and Precision@100. ](#similar-companies) [\[02\] **Build a list** Describe the companies you want. Ranked on F1 for a complete set. ](#build-a-list) 

\[00\] TL;DR

## Best API for GTM list building, by input

There is no single best API across both jobs. Read the ranking that matches how you will query.

* **Similar companies, long list:** CompanyEnrich: 73.5% Precision@100 across 48 seed companies.
* **Similar companies, short list:** CompanyEnrich: 91.9% Precision@10.
* **Build a list, search-only:** Parallel basic: 46.5% F1 on 45 multi-constraint company searches. Snippets, no fetch.
* **Build a list, search & fetch:** Exa deep: 48.2% F1\. Agent opens pages.

\[01\] similar companies

## Search by similar companies

One seed company in. A list of lookalikes out. Same seeds, same judge panel. Precision@10 is the shortlist a rep works by hand. Precision@100 is the long list that feeds a sequence.

[Full lookalike benchmark, including the per-seed matrix →](https://openbenchmarks.com/lookalikes) 

long list Precision@100: how relevant a vendor stays a hundred companies deep. The metric for lists that feed automated sequences. 3 vendors cannot appear here: their endpoint returns fewer than 100 results. 

__Long-list lookalike quality: aggregate Precision@100 by company lookalike API vendor__
| Rank | Vendor | Precision@100 | Avg latency | Relevant / $1 at 100 |
| --- | --- | --- | --- | --- |
| 1 | [CompanyEnrich](https://companyenrich.com "Open CompanyEnrich in a new tab") | 73.5% | 1,323 ms | 16 |
| 2 | [Seltz](https://seltz.ai "Open Seltz in a new tab") | 63.4% | 4,835 ms | 12,683 |
| 3 | [Extruct](https://www.extruct.ai "Open Extruct in a new tab") | 61.1% | 2,361 ms | 624 |
| 4 | [Ocean.io](https://www.ocean.io "Open Ocean.io in a new tab") | 59.5% | 2,444 ms | 37 |
| 5 | [Parallel](https://parallel.ai "Open Parallel in a new tab") | 56.9% | 2,680 ms | 11,383 |
| 6 | [Exa](https://exa.ai "Open Exa in a new tab") | 48.6% | 3,014 ms | 501 |
| 7 | [Discolike](https://discolike.com "Open Discolike in a new tab") | 34.6% | 1,164 ms | 66 |

short list Precision@10: how relevant the top of the list is. The metric that matters when a person works the results by hand and only the first few rows get touched. Every measured vendor appears here, and the only question asked of them is whether the companies are right. 

__Short-list lookalike quality: aggregate Precision@10 by company lookalike API vendor__
| Rank | Vendor | Precision@10 |
| --- | --- | --- |
| 1 | [CompanyEnrich](https://companyenrich.com "Open CompanyEnrich in a new tab") | 91.9% |
| 2 | [PredictLeads](https://predictleads.com "Open PredictLeads in a new tab") | 89.8% |
| 3 | [Seltz](https://seltz.ai "Open Seltz in a new tab") | 84.4% |
| 4 | [Exa](https://exa.ai "Open Exa in a new tab") | 80.8% |
| 5 | [Extruct](https://www.extruct.ai "Open Extruct in a new tab") | 75.0% |
| 6 | [Ocean.io](https://www.ocean.io "Open Ocean.io in a new tab") | 74.3% |
| 7 | [Parallel](https://parallel.ai "Open Parallel in a new tab") | 69.2% |
| 8 | [ZoomInfo](https://gtm.ai "Open ZoomInfo in a new tab") | 67.1% |
| 9 | [Discolike](https://discolike.com "Open Discolike in a new tab") | 41.9% |
| 10 | [CUFinder](https://cufinder.io "Open CUFinder in a new tab") | 38.9% |

\[02\] build a list

## Build a list

Describe the companies you want in plain language, with three or four constraints. The agent has to return the complete set. Ranked on F1\. Search-only and search & fetch stay separate. Model-only baseline is F1 20.1%.

[Full multi-turn company search benchmark →](https://openbenchmarks.com/multi-turn-company-search) 

### Web Search only

__Build a list, search-only: ranked by F1__
| Provider | Endpoint & configuration | F1 | Precision | Recall | Exact set |
| --- | --- | --- | --- | --- | --- |
| [Parallel basic](https://parallel.ai "Open Parallel basic in a new tab") | POST /v1/search mode=basic parallel-basic | **46.5 ± 1.9** | 88.7 ± 0.9 | 34.4 ± 2.0 | 3.7 ± 2.6 |
| [Exa deep](https://exa.ai "Open Exa deep in a new tab") | POST /search type=deep exa-deep | **45.4 ± 2.0** | 83.2 ± 3.0 | 33.7 ± 1.4 | 1.5 ± 1.3 |
| [Parallel advanced](https://parallel.ai "Open Parallel advanced in a new tab") | POST /v1/search mode=advanced parallel-advanced | **44.2 ± 1.4** | 87.6 ± 3.4 | 32.0 ± 1.6 | 2.2 ± 0.0 |
| [Exa instant](https://exa.ai "Open Exa instant in a new tab") | POST /search type=instant exa-instant | **43.3 ± 1.0** | 82.6 ± 3.8 | 32.2 ± 0.5 | 3.0 ± 1.3 |
| [Linkup fast](https://www.linkup.so "Open Linkup fast in a new tab") | POST /v1/search depth=fast linkup-fast | **41.1 ± 1.7** | 82.8 ± 1.0 | 30.3 ± 1.5 | 0.7 ± 1.3 |
| [Tavily advanced](https://tavily.com "Open Tavily advanced in a new tab") | POST /search search\_depth=advanced tavily-advanced | **41.1 ± 2.3** | 83.7 ± 4.2 | 29.8 ± 1.7 | 2.2 ± 0.0 |
| [Linkup standard](https://www.linkup.so "Open Linkup standard in a new tab") | POST /v1/search depth=standard linkup-standard | **40.6 ± 0.9** | 84.0 ± 7.9 | 29.7 ± 1.4 | 1.5 ± 2.6 |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights | **38.6 ± 0.8** | 79.3 ± 4.9 | 28.3 ± 0.9 | 4.4 ± 0.0 |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights · knowledge=core | **38.1 ± 0.6** | 80.9 ± 1.6 | 27.4 ± 0.9 | 3.0 ± 1.3 |
| [Parallel fast](https://parallel.ai "Open Parallel fast in a new tab") | POST /v1/search mode=fast parallel-fast | **38.0 ± 2.0** | 79.9 ± 4.6 | 27.5 ± 1.4 | 1.5 ± 1.3 |
| [Perplexity](https://www.perplexity.ai "Open Perplexity in a new tab") | POST /search search\_context\_size=low | **37.8 ± 2.1** | 79.3 ± 5.7 | 26.8 ± 1.4 | 2.2 ± 2.2 |
| [Tavily basic](https://tavily.com "Open Tavily basic in a new tab") | POST /search search\_depth=basic tavily-basic | **36.5 ± 3.2** | 82.5 ± 1.9 | 25.7 ± 2.7 | 1.5 ± 1.3 |
| [Parallel turbo](https://parallel.ai "Open Parallel turbo in a new tab") | POST /v1/search mode=turbo parallel-turbo | **34.7 ± 2.4** | 80.0 ± 5.2 | 24.8 ± 2.4 | 1.5 ± 1.3 |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=standard · full\_content=false · focus=general | **30.7 ± 1.4** | 70.3 ± 3.3 | 21.3 ± 1.1 | 0.7 ± 1.3 |
| [Firecrawl](https://firecrawl.dev "Open Firecrawl in a new tab") | POST /v2/search firecrawl | **30.4 ± 1.1** | 77.3 ± 4.4 | 20.7 ± 0.7 | 2.2 ± 0.0 |
| [Brave Search](https://brave.com/search/api/ "Open Brave Search in a new tab") | GET /res/v1/web/search brave | **28.0 ± 1.7** | 66.9 ± 8.5 | 19.3 ± 0.5 | 0.7 ± 1.3 |
| [TinyFish](https://www.tinyfish.ai "Open TinyFish in a new tab") | GET api.search.tinyfish.ai tinyfish | **26.6 ± 1.3** | 64.7 ± 1.5 | 17.9 ± 0.8 | 1.5 ± 1.3 |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=lite · full\_content=false · focus=general | **25.3 ± 1.1** | 62.8 ± 1.9 | 17.6 ± 1.2 | 1.5 ± 1.3 |
| [Seltz](https://seltz.ai "Open Seltz in a new tab") | POST /v1/search scope=companies seltz-companies | **14.5 ± 0.9** | 40.0 ± 3.1 | 9.4 ± 0.7 | 0.0 ± 0.0 |
| [SERP (RapidAPI)](https://rapidapi.com/herosAPI/api/google-search74 "Open SERP (RapidAPI) in a new tab") | GET google-search74.p.rapidapi.com serp | **0.4 ± 0.6** | 0.7 ± 1.3 | 0.3 ± 0.4 | 0.0 ± 0.0 |

F1, precision, recall, and exact-set accuracy are percentages reported as mean ± sample SD across three independent runs; each run aggregates all 45 questions. SD is measured in percentage points.

### Web Search + Fetch

__Build a list, search & fetch: ranked by F1__
| Provider | Endpoint & configuration | F1 | Precision | Recall | Exact set |
| --- | --- | --- | --- | --- | --- |
| [Exa deep](https://exa.ai "Open Exa deep in a new tab") | POST /search type=deep exa-deep | **48.2 ± 2.1** | 89.4 ± 1.2 | 36.0 ± 2.2 | 2.2 ± 2.2 |
| [Perplexity](https://www.perplexity.ai "Open Perplexity in a new tab") | POST /search search\_context\_size=high | **46.6 ± 2.0** | 87.7 ± 5.9 | 34.7 ± 1.1 | 2.2 ± 2.2 |
| [Exa instant](https://exa.ai "Open Exa instant in a new tab") | POST /search type=instant exa-instant | **44.9 ± 0.9** | 85.9 ± 2.5 | 33.5 ± 0.9 | 5.2 ± 1.3 |
| [Parallel basic](https://parallel.ai "Open Parallel basic in a new tab") | POST /v1/search mode=basic parallel-basic | **42.3 ± 1.1** | 81.3 ± 2.8 | 31.3 ± 1.1 | 3.0 ± 1.3 |
| [Parallel advanced](https://parallel.ai "Open Parallel advanced in a new tab") | POST /v1/search mode=advanced parallel-advanced | **42.2 ± 1.1** | 87.6 ± 0.3 | 30.1 ± 1.1 | 2.2 ± 0.0 |
| [Linkup standard](https://www.linkup.so "Open Linkup standard in a new tab") | POST /v1/search depth=standard linkup-standard | **42.0 ± 1.8** | 90.7 ± 2.0 | 30.5 ± 2.0 | 3.0 ± 3.4 |
| [Tavily advanced](https://tavily.com "Open Tavily advanced in a new tab") | POST /search search\_depth=advanced tavily-advanced | **41.0 ± 1.3** | 89.4 ± 6.0 | 29.1 ± 0.7 | 2.2 ± 0.0 |
| [Linkup fast](https://www.linkup.so "Open Linkup fast in a new tab") | POST /v1/search depth=fast linkup-fast | **39.9 ± 1.3** | 85.3 ± 3.6 | 28.6 ± 1.3 | 0.7 ± 1.3 |
| [Parallel fast](https://parallel.ai "Open Parallel fast in a new tab") | POST /v1/search mode=fast parallel-fast | **39.3 ± 3.3** | 82.3 ± 6.6 | 28.2 ± 2.0 | 2.2 ± 0.0 |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights | **38.5 ± 1.6** | 85.2 ± 2.7 | 26.9 ± 1.7 | 0.7 ± 1.3 |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights · knowledge=core | **38.5 ± 2.4** | 78.2 ± 2.5 | 28.3 ± 3.0 | 3.7 ± 1.3 |
| [Tavily basic](https://tavily.com "Open Tavily basic in a new tab") | POST /search search\_depth=basic tavily-basic | **38.1 ± 1.4** | 81.2 ± 5.9 | 27.8 ± 0.7 | 2.2 ± 0.0 |
| [Parallel turbo](https://parallel.ai "Open Parallel turbo in a new tab") | POST /v1/search mode=turbo parallel-turbo | **36.0 ± 3.5** | 83.6 ± 4.0 | 25.0 ± 2.6 | 0.0 ± 0.0 |
| [Firecrawl](https://firecrawl.dev "Open Firecrawl in a new tab") | POST /v2/search firecrawl | **33.2 ± 2.1** | 83.3 ± 0.8 | 22.7 ± 1.8 | 1.5 ± 1.3 |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=standard · full\_content=false · focus=general · extract formats=\[markdown\] | **31.3 ± 1.8** | 73.2 ± 1.9 | 21.7 ± 1.6 | 1.5 ± 1.3 |
| [TinyFish](https://www.tinyfish.ai "Open TinyFish in a new tab") | GET api.search.tinyfish.ai tinyfish | **30.2 ± 3.5** | 70.9 ± 11.3 | 20.9 ± 2.5 | 0.0 ± 0.0 |
| [Brave Search](https://brave.com/search/api/ "Open Brave Search in a new tab") | GET /res/v1/web/search brave | **29.4 ± 1.6** | 73.5 ± 5.8 | 20.4 ± 0.9 | 1.5 ± 1.3 |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=lite · full\_content=false · focus=general · extract formats=\[markdown\] | **27.1 ± 1.5** | 68.5 ± 4.4 | 18.7 ± 0.9 | 2.2 ± 0.0 |
| [Seltz](https://seltz.ai "Open Seltz in a new tab") | POST /v1/search scope=companies seltz-companies | **16.3 ± 1.5** | 49.5 ± 2.4 | 10.2 ± 1.2 | 0.0 ± 0.0 |
| [SERP (RapidAPI)](https://rapidapi.com/herosAPI/api/google-search74 "Open SERP (RapidAPI) in a new tab") | GET google-search74.p.rapidapi.com serp | **0.0 ± 0.0** | 0.0 ± 0.0 | 0.0 ± 0.0 | 0.0 ± 0.0 |

F1, precision, recall, and exact-set accuracy are percentages reported as mean ± sample SD across three independent runs; each run aggregates all 45 questions. SD is measured in percentage points.

\[03\] faq

## Best API for GTM list building: FAQ

### What is the best API for GTM list building in 2026?

Pick by input. Similar companies (a seed account in, lookalikes out) is ranked on Precision@100 / Precision@10\. CompanyEnrich leads the long list at 73.5% Precision@100\. Build a list (describe the ICP, get a company set) is ranked on F1\. Search-only leader: Parallel basic at 46.5% F1\. Search & fetch leader: Exa deep at 48.2% F1\. Those two jobs do not share a winner.

### What is the best API to make company lists?

Same split. If the list is companies like these, use the lookalike ranking. If you are building a list from a brief (industry, stage, geography, hiring), use the company-search ranking. Filter UIs in ZoomInfo, Apollo, or Clay are a third input and are not scored on either table.

### What is the best web search API for company search?

That job is Build a list on this page: 45 questions with three or four constraints, scored on F1 against a human-reviewed gold set. Search-only: Parallel basic at 46.5% F1\. Search & fetch: Exa deep at 48.2% F1\. It is not a lookalike API and not a one-shot news lookup. Full method: multi-turn company search.

### What is the best API for GTM prospecting?

Prospecting here means account discovery, not contact finders or sequencing. Similar companies and Build a list are the two measured discovery APIs on this page. Enrichment, funding data, and work-email APIs are later pipeline steps and have their own rankings.

### Is there a best API for GTM overall?

No. GTM is a stack. This page ranks list building (finding the accounts). It does not rank enrichment, intent, or outbound. Do not average the two tables on this page into one GTM winner.

### How is similar companies different from Build a list?

Similar companies: one seed domain in, a ranked list of lookalikes out, scored on whether a judge panel finds those companies relevant. Build a list: a multi-part description in, a complete company set out, scored on precision, recall, and F1 against gold. A vendor that leads one job can lose the other.

### Is this independent, with open source code and open data?

Yes. No vendor pays for inclusion or rank. Lookalikes: identical seeds, public request/response and judge prompts (https://github.com/openbenchmarks-labs/lookalikes). Build a list: question, prompt, model, and budgets held constant (https://github.com/openbenchmarks-labs/multi-turn-company-search; dataset https://huggingface.co/datasets/openbenchmarks/OB-Company-Websearch).

Openbenchmarks open source code + open data 

[← lookalike benchmark](https://openbenchmarks.com/lookalikes) [multi-turn company search](https://openbenchmarks.com/multi-turn-company-search) [B2B prospecting tools](https://openbenchmarks.com/lookalikes/b2b-prospecting-tools) [lookalike source](https://github.com/openbenchmarks-labs/lookalikes) [company search source](https://github.com/openbenchmarks-labs/multi-turn-company-search) © 2026 Openbenchmarks