legal benchmark
Legal Agent Benchmark
The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work. Tasks are scored under an all-pass standard against expert-curated rubrics, where a task passes only if every required rubric criterion (facts, conclusions, citations, structure, and analytical moves) passes.
Updated Aug 11, 2026
Models13
Model coverage13
MetricScore
EvidenceB
Legal Agent Benchmark Ranking
Higher score ranks better on this benchmark.
| 01 | AN | 13.3% | 100.0% | 13 | C | |
| 02 | AN | 11.7% | 91.7% | 13 | C | |
| 03 | AN | 7.1% | 83.3% | 13 | B | |
| 04 | AN | 5.8% | 75.0% | 13 | C | |
| 05 | AN | 5.4% | 66.7% | 13 | B | |
| 06 | AN | 4.2% | 58.3% | 13 | B | |
| 07 | OP | 2.1% | 50.0% | 13 | B | |
| 08 | GO | 0.8% | 41.7% | 13 | B | |
| 09 | OP | 0.4% | 33.3% | 13 | B | |
| 10 | GO | 0.0% | 25.0% | 13 | B | |
| 11 | GO | 0.0% | 16.7% | 13 | B | |
| 12 | GO | 0.0% | 8.3% | 13 | B | |
| 13 | OP | 0.0% | 0.0% | 13 | B |
Legal Agent Benchmark Score Distribution
A closer view of the leading scores on this benchmark.
Legal Agent Benchmark Highlights
The leading models and scores on this benchmark.
What is Legal Agent Benchmark?
What Legal Agent Benchmark measures and how its scores work.
The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work. Tasks are scored under an all-pass standard against expert-curated rubrics, where a task passes only if every required rubric criterion (facts, conclusions, citations, structure, and analytical moves) passes.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Legal Agent Benchmark
- Modality
- text
- Primary category
- legal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- legal-agent-benchmark|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Legal Agent Benchmark.
Which model scores highest on Legal Agent Benchmark?
Claude Fable 5 is currently ranked first with 13.3%.
What does Legal Agent Benchmark measure?
The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work. Tasks are scored under an all-pass standard against expert-curated rubrics, where a task passes only if every required rubric criterion (facts, conclusions, citations, structure, and analytical moves) passes.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
13 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.