GDPx Benchmark: Best Frontier AI Scores 12% on Real Work, Zero on Finance and Legal
SemiAnalysis's GDPx benchmark tested 13 frontier AI models on 206 real professional tasks. Best score: 12%. Finance and legal returned zero across every model. — Tech Times
· share to X · Bluesky ·Coverage (1 written)
- Tech Times first GDPx Benchmark: Best Frontier AI Scores 12% on Real Work, Zero on Finance and Legal Earl Bensen · 15h ago

Comments
Join Ludosauce to join the conversation.
No comments yet. Start it off.