The information on this website is generated using AI and we cannot guarantee its accuracy. Please use it as reference information only.

Anthropic’s Claude Opus 5.5 tops GDPx benchmark at 12.0%

Nov 2, 2026 02:22 (3h ago)

Verifying

SemiAnalysis released GDPx to assess general agentic capabilities across frontier AI models.
Claude Opus 5.5 led GDPx v1.0 with a 12.0% overall success rate.
SemiAnalysis plans GDPx updates every 3 to 6 months with feedback and additional partners.