J1-Bench

What is J1-Bench?

J1-Bench is an interactive and comprehensive legal benchmark where LLM agents engage in diverse legal scenarios, completing tasks through interactions with…

Released

2025-07-17

Evaluates

智能体, Agent, legal agent, interactive benchmark, legal benchmark, 任务执行, Task Execution, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/J1-Bench

J1-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2507.04037
• Code https://github.com/FudanDISC/J1Bench
• Dataset https://huggingface.co/datasets/CharlesBeaumont/J1-Eval_Dataset

Which sources cite J1-Bench?

• J1-Bench

Related 智能体, Agent, legal agent, interactive benchmark, legal benchmark, 任务执行, Task Execution, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard