Update
SemiAnalysis Unveils GDPx Benchmark
Research firm SemiAnalysis has released the GDPx benchmark, a new AI test targeting 11 high-value domains where frontier AI is expected to earn its first trillion dollars. The top-scoring model, Claude Opus 5.5 from Anthropic, achieved a 12.0% overall success rate on the first leaderboard. The benchmark evaluates frontier models across domains such as chip design, biology, and finance, excluding sectors like government and insurance due to lower ROI potential for AI applications.