Sign in

Sign up

Elicit Blog /

Pradyumna Prasad

Background pattern, rich with textural elements

Comparing Elicit to Web Search APIs

On BioASQ, Elicit achieves the highest recall scoring 60.3% at 50 papers, versus 40.3% for the next-best system

We evaluate Elicit search against web search engines on the BioASQ benchmark

Machine learning

Evaluating Elicit’s Paper Search

Elicit outperformed five other search systems on BioASQ, retrieving more of the papers biomedical experts rely on.

Features

Evaluating Elicit’s Systematic Literature Review Capabilities

Elicit hit 95% search recall, 97% abstract screening, 99% full-text screening, and 96% extraction across 994 Cochrane reviews.

Features

Claude Opus 4.5

Evaluating Claude Opus 4.5

Claude Opus 4.5 is better than Sonnet 4.5, Google Gemini 3 Pro, and OpenAI GPT 5 at data extraction and writing reports with fewer hallucinations.

Features

Comparing Elicit to Web Search APIs

On BioASQ, Elicit achieves the highest recall scoring 60.3% at 50 papers, versus 40.3% for the next-best system

We evaluate Elicit search against web search engines on the BioASQ benchmark

Machine learning

Evaluating Elicit’s Paper Search

Elicit outperformed five other search systems on BioASQ, retrieving more of the papers biomedical experts rely on.

Features

Evaluating Elicit’s Systematic Literature Review Capabilities

Elicit hit 95% search recall, 97% abstract screening, 99% full-text screening, and 96% extraction across 994 Cochrane reviews.

Features

Claude Opus 4.5

Evaluating Claude Opus 4.5

Claude Opus 4.5 is better than Sonnet 4.5, Google Gemini 3 Pro, and OpenAI GPT 5 at data extraction and writing reports with fewer hallucinations.

Features