Legal Agent Benchmark

The Legal Agent Benchmark evaluates AI agents on complex legal work, testing their ability to complete realistic professional legal tasks autonomously.

Claude Fable 5 from Anthropic currently leads the Legal Agent Benchmark leaderboard with a score of 0.133 across 1 evaluated AI models.

About this benchmark

What Legal Agent Benchmark measures

Legal Agent Benchmark is a text benchmark that evaluates large language models on legal, reasoning, and agents tasks. LLM Stats tracks 1 model on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.1, with the leader reaching 0.1.

Compare leaders on the best AI for legal, best AI for reasoning and best AI for agents leaderboards.

AnthropicClaude Fable 5 leads with 13.3%.

Progress Over Time

Interactive timeline showing model performance evolution on Legal Agent Benchmark

State-of-the-art frontier
Open
Proprietary

Legal Agent Benchmark Leaderboard

1 models
ContextCostLicense
1
Anthropic
Anthropic
1.0M$10.00 / $50.00
Notice missing or incorrect data?

FAQ

Common questions about Legal Agent Benchmark.

What is the Legal Agent Benchmark benchmark?

The Legal Agent Benchmark evaluates AI agents on complex legal work, testing their ability to complete realistic professional legal tasks autonomously.

What is the Legal Agent Benchmark leaderboard?

The Legal Agent Benchmark leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Claude Fable 5 by Anthropic leads with a score of 0.133. The average score across all models is 0.133.

What is the highest Legal Agent Benchmark score?

The highest Legal Agent Benchmark score is 0.133, achieved by Claude Fable 5 from Anthropic.

How many models are evaluated on Legal Agent Benchmark?

1 models have been evaluated on the Legal Agent Benchmark benchmark, with 0 verified results and 1 self-reported results.

What categories does Legal Agent Benchmark cover?

Legal Agent Benchmark is categorized under legal, reasoning, and agents. The benchmark evaluates text models.

Which model offers the best value on Legal Agent Benchmark?

Among models scoring within 10% of the leader, Claude Fable 5 from Anthropic is the cheapest, at $10.00 per million input tokens with a score of 0.133.

How recent are the Legal Agent Benchmark leaderboard results?

The Legal Agent Benchmark leaderboard was last updated in June 2026 and currently includes 1 evaluated models.

More evaluations to explore

Related benchmarks in the same category

View all legal
GPQA

A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.

reasoning
221 models
MMLU-Pro

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.

legal
125 models
AIME 2025

All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

reasoning
113 models
MMLU

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

legal
99 models
SWE-Bench Verified

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

reasoning
98 models
Humanity's Last Exam

Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

reasoningmultimodal
80 models