Skip to main content
benchlm.ai

Artificial Analysis Harvey LAB-AA (AA Harvey LAB)

An independently evaluated legal-agent benchmark from Artificial Analysis.

Data verified

Benchmark score on AA Harvey LAB — July 9, 2026

BenchLM mirrors the published score view for AA Harvey LAB. Grok 4.5 leads the public snapshot at 13.3% , followed by Claude Opus 4.8 (7.5%) and GLM-5.2 (7.5%). BenchLM does not use these results to rank models overall.

1Closed

Grok 4.5

xAI

grok-4-5

13.3%
Overall —Context 500K
2Closed

Claude Opus 4.8

Anthropic

claude-opus-4-8

7.5%
Overall 85Context 1M
3Open

GLM-5.2

Z.AI

glm-5-2

7.5%
Overall 81Context 1M
16 modelsAgenticCurrentDisplay onlyUpdated July 9, 2026

The published AA Harvey LAB snapshot is tightly clustered at the top: Grok 4.5 sits at 13.3%, while the third row is only 5.8 points behind. The broader top-10 spread is 11.6 points, so the benchmark still separates strong models even when the leaders cluster.

16 models have been evaluated on AA Harvey LAB. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. AA Harvey LAB is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA Harvey LAB

Year

2026

Tasks

Legal agent tasks

Format

Task success rate

Difficulty

Professional legal work

Stored as a display-only agentic row.

Artificial Analysis Harvey LAB-AA Benchmark Leaderboard

BenchLM freshness & provenance

Version

AA Harvey LAB 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Benchmark score table (16 models)

1
Grok 4.5grok-4-5
13.3%
2
Claude Opus 4.8claude-opus-4-8
7.5%
3
GLM-5.2glm-5-2
7.5%
4
MiniMax M3minimax-m3
6.7%
5
Claude Sonnet 5claude-sonnet-5
5.0%
6
GPT-5.6 Lunagpt-5-6-luna
5.0%
7
GPT-5.5gpt-5-5
4.2%
8
Nemotron 3 Ultranemotron-3-ultra-500b
3.3%
9
GPT-5.6 Terragpt-5-6-terra
2.5%
10
Gemini 3.5 Flashgemini-3-5-flash
1.7%
11
Mistral Medium 3.5 128Bmistral-medium-3-5-128b
0.8%
12
Gemini 3.1 Progemini-3-1-pro
0.0%
13
Kimi K2.6kimi-2-6
0.0%
14
GPT-OSS 120Bgpt-oss-120b
0.0%
15
Grok 4.3grok-4-3
0.0%
16
Gemma 4 31Bgemma-4-31b
0.0%

FAQ

What does AA Harvey LAB measure?

An independently evaluated legal-agent benchmark from Artificial Analysis.

Which model scores highest on AA Harvey LAB?

Grok 4.5 by xAI currently leads with a score of 13.3% on AA Harvey LAB.

How many models are evaluated on AA Harvey LAB?

16 AI models have been evaluated on AA Harvey LAB on BenchLM.

Compare Top Models on AA Harvey LAB

Grok 4.5 vs Claude Opus 4.8Claude Opus 4.8 vs GLM-5.2GLM-5.2 vs MiniMax M3MiniMax M3 vs Claude Sonnet 5
Last updated: July 9, 2026 · BenchLM version AA Harvey LAB 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.