Domains: Legal
Skills: Knowledge WorkAgenticWritingReasoningLong Context

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
10/10
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"

Grading

Weight 15%
10/10
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
Rank Model Official Score Percentile
#1GPT-6.2 Astra max OpenAI15.0%100.0p
#2Muse Wonder Full max Meta13.1%100.0p
#3GPT-6.2 Sol max OpenAI11.1%97.7p
#4Muse Wonder max Meta10.0%93.9p
#5Grok 4.7 xhigh SpaceXAI9.4%88.2p
#5Qwen4 Max xhigh Alibaba9.4%88.2p
#7Muse Spark 1.3 max Meta8.9%82.6p
#8GPT-6 Astra max OpenAI8.6%78.8p
#9Claude Fable 5.2 max Anthropic7.2%75.0p
#10GPT-6.1 Sol max OpenAI6.9%71.2p
#11Claude Fable 5.1 max Anthropic6.4%67.4p
#12Claude Opus 5.5 max Anthropic4.2%63.7p
#13Gemini 4 Argon high Google3.9%59.9p
#14GPT-6 Sol max OpenAI3.6%56.1p
#15GPT-6 Luna max OpenAI3.3%52.3p

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit Harvey LAB-AA v1.1 Tier S 10/10
[![BenchAudit Tier S](https://benchaudit.org/badges/harvey-lab-aa-v1-1.svg)](https://benchaudit.org/benchmarks/harvey-lab-aa-v1-1/)