Skip to content
Eval Suites50

Domain: Finance / Health / Legal eval suites

Domain suites test finance, health, legal, and accessibility tasks where wrong answers carry real cost, often with expert-written rubrics.

6 of 6 suites

HealthBench

production

Health conversations scored against physician-written rubrics for accuracy, safety, communication, and context-seeking.

Size
5,000 conversations
Runs with
Inspect AI
License
MIT
Category
Domain

Financial-analyst tasks using SEC filings. The harness is open source; only 50 questions are public, the rest are private or licensable.

Size
537 questions (50 public)
Runs with
Python
License
Not stated
Category
Domain

LegalBench

production

Collaboratively built legal reasoning tasks: issue spotting, rule recall, interpretation, and rhetorical analysis. Licenses vary by task.

Size
162 tasks
Runs with
Python
License
Not stated
Category
Domain

Multiple-choice questions from medical licensing exams, testing clinical knowledge and diagnostic reasoning.

Size
12,723 English questions
Runs with
Python
License
Not stated
Category
Domain

FinQA

starter

Numerical reasoning over text and tables from earnings reports, with annotated reasoning programs.

Size
8,281 QA pairs
Runs with
Python
License
Not stated
Category
Domain

Runs automated accessibility checks on HTML that LLMs generate. Automated checks catch many issues but don't prove full WCAG conformance.

Size
32 prompt cases
Runs with
Node CLI
License
MIT
Category
Domain

Size and license come from each suite's primary source. Not stated means the source doesn't declare a license; check the repo before commercial use.