Atlas

Benchmarks

← All benchmarks

Harvey HLAB - Criteria Pass Rate - Real Estate

Professional Work · 2026-05-06

The Real Estate practice-area split of Harvey's Legal Agent Benchmark held-out evaluation criteria pass rate. This reports pooled rubric criteria passed within that split and is distinct from the all-pass task-score split.

Top models (higher is better)

ModelScore
Muse Spark 1.195.6
Kimi K394.8
Grok 4.593.6
Claude Fable 593.3
Claude Opus 593.0
GPT-5.592.7
GLM-5.291.8
Opus 4.891.0
GPT-5.6 Luna90.7
Sonnet 4.690.4
Qwen3.7-Max90.1
DeepSeek-V4-Pro89.2
GPT-5.6 Terra88.6
MiniMax M388.3
Sonnet 586.9
Gemini 3.5 Flash86.3
Kimi K2.681.9
GPT-5.480.8
Gemini 3.6 Flash79.3
GPT-5.6 Sol79.0
Inkling76.1
Grok 4.370.3
Qwen3.7-Plus65.6
Gemini 3.5 Flash-Lite64.1
Laguna M.156.9
GLM-5.149.9
Laguna XS.241.1
Loading Atlas data…