Vertical & Agentic Benchmarks
MedQA, LegalBench, SWE-bench, tau-bench
Domain benchmarks (MedQA/HealthBench, LegalBench, FinBen, SWE-bench, tau-bench for agents) are how buyers in each vertical evaluate whether a model is fit for regulated use. They translate abstract capability into vertical procurement decisions and increasingly drive model marketing.
Examples
HealthBench, LegalBench, tau-bench
Role
Vertical fitness-for-use eval
How it fits the stack
Vertical & Agentic Benchmarks with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.
Vertical & Agentic Benchmarks in the AI stack. Vertical & Agentic Benchmarks with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.
Graph data (text) — 3 entities, 2 relationships
- Healthcare & Life Sciences AI —uses→ Vertical & Agentic Benchmarks
- Legal AI —uses→ Vertical & Agentic Benchmarks