Opus 5.5 leads the new GDPx benchmark with 12%. GDPx gives AI agents 206 tasks… · @qwerty__cs · TwKit

@qwerty__cs

Opus 5.5 leads the new GDPx benchmark with 12%. GDPx gives AI agents 206 tasks across 11 fields, including chip design, finance and law. Its score combines pass/fail and partial credit, averaged equally across domains. Current leaders: Opus 5.5 at 12.0%, Gemini 4 Carbon at 10.9%, and GPT-6 Astra at 9.6%. https://gdpx.semianalysis.com/

曝光 323 · 评论 1 · 点赞 2 · 书签 0