Grok 4.3 Takes the Top Spot on Legal and Financial Benchmarks, Outpacing GPT-5.1
xAI's latest model now leads private benchmarks for case law reasoning and corporate finance analysis — domains where precision matters more than generality.
Grok 4.3 has claimed the number one position on two specialized benchmarks that matter to professionals: CaseLaw v2, where it scored 79.31%, and CorpFin v2, where it hit 68.53%, according to results shared by @XFreeze. Both scores reportedly surpass GPT-5.1's performance on the same tasks. Elon Musk amplified the results with a characteristically terse 'Try Grok' post that went viral.
Unlock the full briefing
Get every story in today's briefing, the full archive, and the daily AI intelligence brief.
All stories today
Full archive
Daily brief
Cancel anytime. Payments powered by Stripe.