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.
More from Models
- 3 weeks with OpenAI Astra 5.2: shines at delegating under messy stacked context — round · 2026-11-18
- Open-weights Inkling climbs from last to top-3 on FutureSim via test-time learning — simonguozirui · 2026-11-18
- GPT-6.2 Astra reportedly launches, with an alleged 100% score on ARC-AGI-3 — patience_cave · 2026-11-18
- OpenAI claims Astra for Law cuts hallucinations 20x vs Opus 5.5, 25x vs Fable 5.2 — sherwinwu · 2026-11-18
- OpenAI cuts Ultrafast pricing 50% for 3 months, brings it to Pro 200 subscribers — OpenAIDevs · 2026-11-18
- GPT-6.2 Astra sets Terminal-Bench Science record: +9 points over GPT-6 Astra at under 1/3 cost — OpenAIDevs · 2026-11-18