CLAUSE
More than 7,500 contracts with deliberate changes across ten categories of anomaly.
Reported results
No comparable score table is recorded in this collection.
What the benchmark measures
More than 7,500 contracts with deliberate changes across ten categories of anomaly.
The evaluated unit is a model response or component output. Read the source for the exact prompt, tool and harness conditions.
How it is scored
Detection accuracy and explanation quality.
Scores remain in the original unit. They are not normalised or combined with results from other benchmarks.
Sources
Tests whether models find and explain deliberately introduced errors.