LawBench

What it measures

20-task Chinese civil and criminal legal system benchmark across statutory memorization, understanding, and judicial application.

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

Average across the source’s legal tasks; task-specific ROUGE and accuracy definitions follow the publication. Prompting settings remain separate.

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

Average across the source’s legal tasks; task-specific ROUGE and accuracy definitions follow the publication. Prompting settings remain separate.

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.