Skip to content

Legal operations

CounselBench-100

Long-horizon legal work across evidence rooms, custody checks, source-grounded findings, and final deliverables.

About CounselBench-100

What it measures

Consult the upstream task verifier.

Scope & limitations

Listed in the catalog; not treated as independently established or famous. Catalog task counts do not prove validated coverage.

Evaluation environment

Dataset-specific harness qualification required.

Source

Original benchmark

Dataset & task catalog ↗