OpenAI Astra for Law tops Harvey LAB-AA v1.1 legal benchmark at 20.8%

ArtificialAnlys · x · 2026-11-18

Artificial Analysis' Harvey LAB-AA v1.1 benchmark tests real-world legal work across 120 private tasks in 24 practice areas, with a hallucination-gated all-pass headline metric. Astra for Law 6.2 — a GPT-6.2 Astra configuration with an expanded integrated legal search index — leads at 20.8%, ahead of GPT-6.2 Astra (max) at 15.0%. It has no publicly available API. Per-task hallucination counts show Astra for Law at 0.03 material flags versus 3.94 for GLM-5.3.

Original post →

More from Models

Models channel →