CategoryAgentic
MeasureHallucination-Gated All-Pass Rate
Tasks120 private legal tasks across 24 practice areas
DifficultyProfessional legal work
Legal-agent task success requiring every rubric criterion to pass and no material hallucination, averaged across three judges.
Harvey LAB-AA v1.1 ranking
2 models with a published Harvey LAB-AA v1.1 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
Models ranked by their published Harvey LAB-AA v1.1 value| Rank | Model | Provider | Hallucination-Gated All-Pass Rate |
|---|
| 1 |  Muse Wonder Full | Meta | 13.1 |
| 2 | Muse Wonder | Meta | 10.0 |
Evidence key: Observed
Rows are ordered by the value Harvey LAB-AA v1.1 Benchmark Leaderboard published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
About Harvey LAB-AA v1.1
What the benchmark measures and how its value is published, from the source’s own record.
What is Harvey LAB-AA v1.1?
Harvey LAB-AA v1.1 is an agentic benchmark published by Harvey LAB-AA v1.1 Benchmark Leaderboard. Legal-agent task success requiring every rubric criterion to pass and no material hallucination, averaged across three judges. Its evaluation set is described by the source as 120 private legal tasks across 24 practice areas. The source rates its difficulty as professional legal work.
How is Harvey LAB-AA v1.1 scored?
Each model's result is published by Harvey LAB-AA v1.1 Benchmark Leaderboard as hallucination-Gated All-Pass Rate. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 2 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale