Elicit Launches General API and MCP With 60.3% Recall Rate on Biomedical Search Benchmark
Elicit announced the general availability of its API and the Model Context Protocol, introducing a rebuilt search engine that achieved a 60.3% recall rate on a biomedical benchmark, compared to 47.4% for the nearest competitor.
The company tested its performance on the BioASQ peer-reviewed dataset against rival platforms including Google Scholar, Semantic Scholar, OpenAlex and Consensus, reporting the highest recall across result depths from 10 to 200 papers. Elicit published a full performance report alongside the launch.
From the sources (2 posts)
@elicitorgThe Elicit API and MCP are now generally available. To support this launch we rebuilt Elicit's search from the ground up and tested whether it actually was better. We picked BioASQ, a peer-reviewed biomedical benchmark to measure our perfo
@stuhlmuellerRT @elicitorg: The Elicit API and MCP are now generally available. To support this launch we rebuilt Elicit's search from the ground up and…