What it measures
510 commercial legal contracts with 13,000+ expert annotations across 41 critical legal clause categories.
Reading the measurement
F1 balances precision and recall. Check both: a system can miss relevant evidence or include unsupported material, and those errors have different consequences. Keep the matching rule, averaging policy and denominator fixed.
Published evaluation
AUPR over the contract-review extraction task, using the paper 0–100 scale. Fixed-recall precision is a separate metric.
Where this fits in an evaluation suite
Synthetic research rewards do not establish live investment performance. Preserve transaction costs, held-out regimes, constraints, and the exact policy behind a reported result.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
AUPR over the contract-review extraction task, using the paper 0–100 scale. Fixed-recall precision is a separate metric.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.