Exa Labs
For Exa LabsSearch & KnowledgeSearch Api

Find Similar Semantic Neighbors

Exa · Exa Labs

Neural web search API — Exa

Evaluates Exa Labs' Find Similar & Semantic Neighbors across 8 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Neural web search API eval coverage.

About Exa Labs

Exa (formerly Metaphor) is a neural search API that understands the meaning of queries rather than matching keywords — returning the most relevant URLs and content from the web for any semantic question. Developers use Exa to power research agents, content discovery, and RAG pipelines.

Employees

~30

Industry

Neural Search API

Headquarters

San Francisco, CA

Website

exa.ai

Sample tests· showing 3 of 8

#InputExpected behaviorCheck
01

User provides seed URL https://example.com/blog/post-1 and wants related reading.

Note /findSimilar deprecated but functional; prefer documented alternatives when available; use findSimilar for URL-seeded semantic neighbors with excludeSourceDomain.

Pass / FailSimilaritymedium
02

SKU ABC-123 appears in unrelated retailers; user asks for similar pages to Amazon listing.

Explain findSimilar is semantic neural similarity on page content, not SKU equality; use search with SKU query for lexical needs.

Pass / FailSimilarityhigh
03

Reader app wants related articles not the same publisher homepage duplicates.

Exclude seed domain to diversify neighbors; explain semantic similarity is not same-URL variants.

Pass / FailSimilaritymedium

Unlock full benchmark

5 more test cases

Use this benchmark

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric.

Rubric criteria

  • Exa Labs
  • Search
  • Find Similar Semantic Neighbors

Recommended for

ExaExa Labs customers

Works with

Related evals

Frequently asked questions

What does the Find Similar Semantic Neighbors eval for Exa Labs Exa test?+

Evaluates Exa Labs' Find Similar & Semantic Neighbors across 8 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Neural web search API eval coverage.

How is the Find Similar Semantic Neighbors eval scored?+

The judge rubric: Grade against expected.ideal_behavior and expected.rubric.

How many test cases does this eval pack include?+

The Find Similar Semantic Neighbors pack for Exa Labs Exa contains 8 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.

How do I run this eval?+

Sign up for Corsac, connect your model or agent endpoint, and run the Find Similar Semantic Neighbors pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.