Exa just launched what it's calling state-of-the-art search over academic literature, and the benchmark numbers are hard to ignore. The company built a dedicated index of roughly 350 million publications and added around 30 million authors to its people index, all queryable through its existing Search API. The pitch: scientific search that actually works the way researchers think, not the way databases are organized.
The problem with academic search today
Anyone who has tried to track down a paper they half-remember knows the pain. Traditional academic search tools like Google Scholar are built around exact keyword matching, author names, and titles. That works fine when you already know what you're looking for. It breaks down completely when all you have is a vague memory of a result, an experimental setup described in plain English, or a question like: "wasn't there a study from the 70s showing dietary cholesterol always raised LDL in primates, even when total cholesterol looked normal?"
Exa searches over the meaning of the query and the contents of the paper, making it possible to retrieve a specific publication from factual clues or an incomplete recollection, without requiring the user to translate the question into the right academic keywords. This is the core shift: from keyword lookup to semantic understanding of what you're actually trying to find.
The numbers behind the claim
Exa created two new benchmarks to measure this. The first tests known-item retrieval, where a searcher provides precise factual clues and the system must identify the exact paper. The second tests
Don't miss what's next in AI
Join 300,000+ engineers and researchers who get the signal, not the noise.
- Full access to in-depth AI research breakdowns
- Be the first to know what's trending before it hits mainstream
- Daily curated papers, repos, and industry moves