ContractEval

Clause-level risk questions derived from CUAD, tested on open and proprietary models.

The evaluated unit is a model response or component output. Read the source for the exact prompt, tool and harness conditions.

Correctness and output effectiveness scores.

Scores remain in the original unit. They are not normalised or combined with results from other benchmarks.

• Primary benchmark source

Extends CUAD from extraction into explanation.