Machine Learning Business & Enterprise5 min reading time

Exa 3.0 Search API Tops Perplexity, Brave and Parallel on 8 Benchmarks

MarkTechPostPublished 5 days ago

Exa Labs released Exa 3.0, an upgraded web search API featuring a larger embedding model and a cheaper search option called Exa Lite. The API claims top performance over Perplexity, Brave, and Parallel on eight benchmarks, with Dynamic Highlights now generally available to improve answer quality efficiently.

#brave #embedding-models #exa-3-0 #exa-labs #parallel #perplexity #search-api #web-search

Exa 3.0 Search API Tops Perplexity, Brave and Parallel on 8 Benchmarks

More in Machine Learning

Google ML Drift Accelerates On-Device AI Inference Across Diverse GPUs

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend