Benchmark Radar
AI BENCHMARK PROFILE

GraphRareBench

General AIKnowledge & ReasoningGraphRareBench team

GraphRareBench evaluates phenotype-driven rare-disease ranking with 2,365 cases, 18,093 target-confounder pairs, and auditable evidence records.

Released
2026-07-27
Readiness
Runnable
Primary field
General AI

Why it matters

Offers a transparent, evidence-aware evaluation for diagnostic systems, measuring retrieval and hard-confounder discrimination in a provenance-preserving setting.

Motivation

Phenotype-driven diagnostic benchmarks usually report the rank of the reference disease, but they rarely reveal which plausible alternatives are ranked above it or what evidence a tool-using model examines before making its decision.

Primary resources

Benchmark Radar records only publicly supported details and links back to primary sources for verification.