Curated AI beats frontier LLMs at pharma asset discovery

TL;DR

A curated AI platform named Gosset outperforms leading web-search-based LLMs in pharmaceutical asset discovery, achieving higher verified drug retrieval with perfect precision and recall on niche oncology and immunology targets.

Contribution

Introduction of Gosset, a curated drug-asset database integrated with an AI chat interface, demonstrating superior performance over frontier web-access LLMs in pharma asset discovery.

Findings

Gosset retrieves 3.2x more verified drugs per query than top frontier systems.

Gosset achieves 100% recall and perfect precision on tested targets.

Curated index can be used as a tool to improve other models' recall.

Abstract

General-purpose LLMs with web search are increasingly used to scout the competitive landscape of pharmaceutical pipelines. We benchmark Gosset -- an AI platform with a chat interface backed by curated target-, modality-, and indication-level drug-asset annotations -- against four frontier systems with web access (Claude Opus 4.7, GPT 5.5, Gemini 3.1 Pro, Perplexity sonar-pro) on ten niche oncology/immunology targets where most of the pipeline lives in the long tail of preclinical and Asian-developed assets. All five systems receive the same natural-language query and the same JSON output schema. Across 10 targets Gosset returns 3.2x more verified drugs per query than the best frontier system, at perfect precision and 100% recall against the cross-system union of verified drugs. The same curated index is exposed as a Gosset MCP server that any frontier model can call as a tool, suggesting that each of these systems can close most of the recall gap by swapping generic web search for a curated index behind the same chat interface.