Four-Factor Integrity Breakdown & Primary-Source Evidence
Access Model: Strictly Private
"Artificial Analysis' implementation of Harvey's Legal Agent Benchmark (LAB), testing AI agents on real-world legal work from Harvey's dataset of 120 private tasks spanning 24 legal practice areas."
Originality
Weight 25%
10/10
Reuse Profile: All Original (0% reuse)
"For each task the agent reads the case documents in a sandbox and produces legal deliverables - memos, disclosure schedules, deposition summaries, redlines, and similar work products - in a single run without live interaction."
Freshness
Weight 20%
10/10
Initial Release: 2026-05Latest Refresh: 2026-10Rolling Updates: No
"October 8, 2026 Announcing Harvey LAB-AA v1.1: adding hallucination checks to raise the bar for agentic legal work"
Integrity: Independent Offline (Leak-Verified)Sandbox: offline isolated
"It checks every deliverable against the task's source documents for hallucinations, grades each criterion with a three-judge panel, and moves the headline from the Criterion Pass Rate to the Hallucination-Gated All-Pass Rate."
Frontier Model Standings on Harvey LAB-AA v1.1
Top 15 active models tracked
Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:
[](https://benchaudit.org/benchmarks/harvey-lab-aa-v1-1/)