lawbench/lawbench
Professional
Law
Knowledge
LawBench: tasks evaluating LLMs on Chinese-law knowledge — legal entity recognition, reading comprehension, criminal-damage calculation, legal consulting — plus an abstention-rate metric.
Run this task
CLI:
inspect eval inspect_harbor/lawbench --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import lawbench
eval(lawbench(), model="openai/gpt-5")Dataset information
| Harbor registry | lawbench/lawbench |
| Inspect task | lawbench |
| Latest digest | sha256:99d2f97d515a3820a657745112aa01a8e2b2e8bf7602d78d3ef53b4bc1c64636 |
| Samples | 1000 |
| Paper | arxiv |
| Source | https://github.com/open-compass/LawBench |
See Task Parameters for the parameter set shared across all Harbor tasks.