frontier model legal work7 min read
We ran GPT-6 Astra against 41 real legal questions
We ran GPT-6 Astra against 41 real legal questions, alongside Claude Opus 5 and GPT-5.6 Luna Pro. Every model we tested got Saudi and Egyptian law wrong while citing the correct article, the failure no citation checker catches.
By HAQQ TeamHAQQ Legal AI on Mobile Blog
Read the full story
Originally published by HAQQ Legal AI on Mobile Blog on Sep 11, 2026.
Comments
Sign in to join the discussion.