benchmarks/company news/best company events api
independently benchmarked · 300 questions · updated Sep 26, 2026

Best Company Events API, 2026

Best Company Events API: Exa fast leads 15 news and search APIs at 99.3% accuracy on 300 company-news questions, independently benchmarked in 2026.

What this page compares. This page ranks measured results from company-news factual lookup (web search APIs and news indexes). The question set mixes layoffs, product launches, funding rounds, acquisitions, leadership changes and expansions. Scores are not reported per event type.

How to read the result. The table ranks every complete run by its score on the same questions. Latency and cost are shown beside it and not blended into the score.

Company-news factual lookup, web search APIs and news indexes, ranked by accuracy

Every row ran the same 300 questions. Provider names link to the official docs for the configuration measured.

RankProviderTypeAccuracyAnswer recall @5Median search time$ / 1k queries$ / 1k correctResult tokensAccuracy / 1k tokensList price
1Exa fasttype=fastWeb search99.3%99.3%569 ms$7.00$7.051,98750.0$7.00 / 1k queries
2Exa instanttype=instantWeb search97.7%97.3%386 ms$7.00$7.172,12845.9$7.00 / 1k queries
3Perplexity lowsearch_context_size=lowWeb search97.3%98.3%1.6 s$5.00$5.14476205$5.00 / 1k queries
4Linkup fastdepth=fast · outputType=searchResultsWeb search96.7%94.7%1.2 s$5.00$5.173,02232.0$5.00 / 1k queries
5SERPlimit=10Web search96.0%95.0%578 ms$3.00$3.13497193$3.00 / 1k queries
7Brave Search llm-contextcount=10Web search94.0%94.7%590 ms$5.00$5.322,06445.6$5.00 / 1k queries
9Parallel basicmode=basicWeb search93.3%92.0%1.8 s$5.00$5.362,33040.1$5.00 / 1k queries
10Nimble standardsearch_depth=standard · full_content=false · focus=generalWeb search93.0%94.3%822 ms$5.00$5.382,73034.1$5.00 / 1k queries
11Tavily advancedsearch_depth=advancedWeb search93.0%92.7%4.2 s$16.00$17.202,21042.1$16.00 / 1k queries
12Linkup standarddepth=standard · outputType=searchResultsWeb search92.0%90.3%2.1 s$5.00$5.432,98330.8$5.00 / 1k queries
14You highlights coreextraction_mode=highlights · knowledge=coreWeb search92.0%89.7%815 ms$5.00$5.432,86232.1$5.00 / 1k queries
15You highlightsextraction_mode=highlightsWeb search90.7%89.7%614 ms$5.00$5.512,83732.0$5.00 / 1k queries
16Tavily basicsearch_depth=basicWeb search87.7%87.7%1.7 s$8.00$9.131,63953.5$8.00 / 1k queries
17Parallel fastmode=fastWeb search86.0%79.0%861 ms$1.00$1.161,83946.8$1.00 / 1k queries
18Nimble litesearch_depth=lite · full_content=false · focus=generalWeb search75.3%75.3%1.4 s$1.10$1.46413183$1.10 / 1k queries
19Parallel turbomode=turboWeb search71.3%66.0%315 ms$1.00$1.401,85338.5$1.00 / 1k queries
20Seltz newsscope=newsNews index58.3%60.0%386 ms$5.00$8.572,91920.0$5.00 / 1k queries
21Autobound news eventsdomain · signal_types=news · signal_subtypes · limit=10News index30.0%25.0%160 ms$36.23$120.7687934.1$9.50 / 1k credits
22PredictLeads news_eventsLLM category pick · categories[] · limit=10News index20.7%20.0%376 ms$40.00$193.5248442.7$40.00 / 1k queries
23Datahyena company eventsdomain · include=funding|acquisitions|exec_movesNews index5.3%6.7%245 ms$38.17$716.0722238$50.00 / 1k credits

How the ranking was measured

  • Every API received the same natural-language question about a recent company event, one search per question, up to 10 results.
  • Each answer is a single verifiable value pinned to an official wire or newsroom URL, fixed before any vendor ran.
  • Accuracy is whether the returned results let the same answering model extract the correct value.
  • Latency is the search request time. Cost is the recorded list price for the calls made, per 1,000 queries and per 1,000 correct answers.
  • The runner and published data are open in openbenchmarks-labs/company-news ↗ and openbenchmarks/OB-News-Websearch ↗. The full methodology is on the Company News Search Benchmark →

Questions answered by this comparison

Which provider leads best Company Events API?

Exa fast leads this table at 99.3% accuracy, on 300 company-news questions.

How was this measured?

Every API received the same natural-language question about a recent company event, one search per question, up to 10 results. Each answer is a single verifiable value pinned to an official wire or newsroom URL, fixed before any vendor ran. Accuracy is whether the returned results let the same answering model extract the correct value. Latency is the search request time. Cost is the recorded list price for the calls made, per 1,000 queries and per 1,000 correct answers.

How should speed and cost be read beside the score?

Exa fast recorded 569 ms median search time and $7.00 per 1,000 queries. The most accurate configuration is rarely the fastest or the cheapest, so each is reported in its own column.

Do vendors pay to be ranked?

No. Inclusion and rank do not depend on vendor payments. Every API used the same questions, answering model and scoring.

What does this page not test?

This page ranks measured results from company-news factual lookup (web search APIs and news indexes). The question set mixes layoffs, product launches, funding rounds, acquisitions, leadership changes and expansions. Scores are not reported per event type.