Browse by task
Benchmark collections
Find the tests closest to your work, then inspect their results and run conditions.
- Finance benchmarksFind tests for financial research, document analysis, accounting, and tax work.11 records
- Legal benchmarksFind tests for legal reasoning, research, case retrieval, and document work.9 records
- Healthcare benchmarksFind tests for health conversations, clinical documentation, billing, and medical questions.10 records
Each collection groups existing evidence by task. It does not calculate a domain score or rank models across different tests.