Legal Index
评估模型在法律领域的表现。评估的能力包括合同法、侵权法、宪法等领域知识,以及法律研究与起草、诉讼支持、合规审查等。
查看代表性工作流The Artificial Analysis Legal Index combines performance across benchmarks chosen for legal practice. We map common tasks from O*NET occupational classifications, then select benchmarks that represent this real-world work. Weights are derived from how often capabilities appear across those tasks.
This composite metric provides a single score for tracking model performance across legal tasks. 所有底层基准测试均由 Artificial Analysis 独立运行。有关评测的实施方式,请参阅我们的智能基准测试方法论。
| 能力 | 权重 | 评测 |
|---|---|---|
| 法律知识 | 30% | AA-Omniscience v1.1 法律准确率 |
| 智能体知识工作 | 25% | AA-Briefcase v1.1 |
| 推理 | 15% | HLE-Diamond |
| 避免幻觉 | 15% | AA-Omniscience v1.1 法律避免幻觉 |
| 长上下文 | 10% | GDP.pdf |
| 智能体工具使用 | 5% | AutomationBench-AA 支持和运营 |
得分
Artificial Analysis Legal Index
Artificial Analysis Legal Index:能力明细
能力明细
Artificial Analysis Legal Index:法律知识
代表性工作流
这些真实工作流重点检验 Legal Index 中权重最高的能力。
示例:Determine whether a non-compete is enforceable under controlling state precedent by gathering the relevant case law, applying each holding to the employee's facts, distinguishing unfavorable rulings, and synthesizing the analysis into a report.
示例:Reconcile US and EU indemnity language in a cross-border M&A share purchase agreement 48 hours before signing to flag irreconcilable conflicts, propose drafting that satisfies both regimes where possible, and deliver a partner-ready redline.
示例:Advise a startup shipping a feature that may trigger unsettled state privacy rules such as the CCPA to ask the clarifying questions, lay out the trade-offs by jurisdiction, surface open legal risks, and recommend a defensible launch posture.
示例:Work a 200,000-document e-discovery production delivered ten days before trial to prioritise responsive material, flag likely privilege issues for attorney review, and draft a deposition outline tied to the strongest exhibits.
示例:Rewrite internal policy for a new financial regulation taking effect in 90 days that clashes with procedures in three business units to produce a unified replacement policy, an implementation plan with named owners, and a training brief grounded in the statute and existing policy library.
示例:Consolidate 40 active litigation matters tracked across three incompatible case-management systems to produce one unified docket, surface conflicting court deadlines, and propose a single workflow going forward.
成本
Artificial Analysis Legal Index:单任务成本
Artificial Analysis Legal Index 与单任务成本
速度
Artificial Analysis Legal Index:单任务耗时
输出 token
Artificial Analysis Legal Index:单任务输出 token
发布日期
Artificial Analysis Legal Index 与发布日期
常见问题
根据 Artificial Analysis Legal Index,目前在法律工作上表现最佳的 AI 模型是 Gemini 4 Carbon (High) (62)、Gemini 4 Carbon (Medium) (59)和Claude Opus 5.5 (Max, Default Fallback) (58)。新模型发布后,排行榜会随之更新。
有。Artificial Analysis Legal Index 是一项独立基准测试,用于衡量 AI 模型在法律工作上的表现。它评估法律知识、智能体知识工作、推理、长文档分析、避免幻觉和智能体工具使用等能力。
Legal Index 是 Artificial Analysis 推出的综合基准测试,用于评估模型在法律领域的表现。评估能力包括合同法、侵权法、宪法等专业知识,以及法律研究与起草、诉讼支持、合规审查等。
Legal Index 按各项能力子分数的加权平均值计算。各项子分数及其权重为:法律知识 (30%)、智能体知识工作 (25%)、推理 (15%)、避免幻觉 (15%)、长上下文 (10%)和智能体工具使用 (5%)。
Legal Index 包含 AA-Omniscience v1.1 法律准确率、AA-Briefcase v1.1、HLE-Diamond、AA-Omniscience v1.1 法律避免幻觉、GDP.pdf和AutomationBench-AA 支持和运营。
在已公布结果的模型中,Gemini 4 Carbon (High) 目前以 62 分位居 Legal Index 榜首。 查看模型
Legal Index 得分越高,表示模型在构成该指数的各项基准测试中整体表现越强。对于特定用例,单项基准测试结果可能比综合得分更具参考价值。