Legal Index
Assesses model performance across the legal domain. Capabilities evaluated include domain-specific knowledge (contract law, tort law, constitutional law), legal research and drafting, litigation support, compliance review, and more.
See representative workflowsThe 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. All underlying benchmarks are run independently by Artificial Analysis. See our Intelligence Benchmarking Methodology for how evaluations are conducted.
| Capability | Weight | Evaluations |
|---|---|---|
| Legal Knowledge | 35% | AA-Omniscience Law Accuracy |
| Agentic Knowledge Work | 25% | GDPval-AA v2 and AA-Briefcase |
| Reasoning | 15% | HLE |
| Long-Context | 10% | LCR and GDP.pdf |
| Non-Hallucination | 10% | AA-Omniscience Law Non-Hallucination |
| Agentic Tool Use | 5% | AutomationBench-AA Support & Operations |
AA-Omniscience: Knowledge and Hallucination BenchmarkGDPval-AA v2 LeaderboardAA-Briefcase: Agentic Knowledge Work Benchmark
Humanity's Last Exam Benchmark LeaderboardArtificial Analysis Long Context Reasoning Benchmark Leaderboard
GDP.pdf Benchmark Leaderboard
AutomationBench-AA: Agentic SaaS Workflow BenchmarkScore
Artificial Analysis Legal Index
Artificial Analysis Legal Index: Capability Breakdown
Capability Breakdown
Artificial Analysis Legal Index: Legal Knowledge
Representative Workflows
Real-world workflows that exercise the capabilities the Legal Index weights most heavily.
Example: 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.
Example: 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.
Example: 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.
Example: 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.
Example: 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.
Example: 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.
Cost
Artificial Analysis Legal Index: Cost per Task
Artificial Analysis Legal Index vs. Cost per Task
Speed
Artificial Analysis Legal Index: Time per Task
Output Tokens
Artificial Analysis Legal Index: Output Tokens per Task
Release Date
Artificial Analysis Legal Index vs. Release Date
Frequently Asked Questions
Based on the Artificial Analysis Legal Index, the top-performing AI models for legal work are currently Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (61), Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (61), and GPT-6 Astra (max) (59). Rankings are updated as new models are released.
Yes. The Legal Index from Artificial Analysis is an independent benchmark of how AI models perform on legal work. It measures performance on the legal domain, including legal knowledge, agentic knowledge work, reasoning, long-context document analysis, non-hallucination, and agentic tool use.
The Legal Index is a composite benchmark from Artificial Analysis that assesses model performance across the legal domain. Capabilities evaluated include domain-specific knowledge (contract law, tort law, constitutional law), legal research and drafting, litigation support, compliance review, and more.
The Legal Index is calculated as a weighted average of its capability sub-scores. The sub-scores and their weights are: Legal Knowledge (35%), Agentic Knowledge Work (25%), Reasoning (15%), Long-Context (10%), Non-Hallucination (10%), and Agentic Tool Use (5%).
The Legal Index includes AA-Omniscience Law Accuracy, GDPval-AA v2, AA-Briefcase, HLE, LCR, GDP.pdf, AA-Omniscience Law Non-Hallucination, and AutomationBench-AA Support & Operations.
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) currently has the highest Legal Index score, with a score of 61 among models with published results. View model
A higher Legal Index score indicates stronger overall performance across the benchmarks that make up the index. For a specific use case, individual benchmark results may be more informative than the composite score.