Claude Opus 5.5 Tops Semi Analysis' GDPx Benchmark, Gemini 4 Carbon Placed Second
7 Articles
7 Articles
Gemini 4 Carbon is ahead of OpenAI in a new independent test and approaches Claude at a cost per task three times lower
In the new, heavy AI benchmark GDPx, which focuses on spending from the sectors that have the highest share of gross domestic product (GDP), the best system achieves just 12 percent. The idea behind the new measurement method is that the first trillion dollars of AI profits are not distributed across the entire economy, but mainly from the
GDPx: Measuring Frontier Model Capabilities Across the Most Valuable Domains
GDPx is a benchmark that covers the most valuable domains for frontier intelligence. It aims to be the world’s best benchmark for measuring general agentic capabilities. We believe the first trillion dollars of AI revenue will be concentrated in sectors that can deploy frontier intelligence at…
SemiAnalysis presented GDPx, a benchmark for evaluating multi-step professional tasks in 11 domains. According to the results attributed to the firm, Claude Opus 5.5 led the ranking with 12% success; Gemini 4 Carbon and GPT-6 Astra excelled in specific areas.
Coverage Details
Bias Distribution
- 50% of the sources are Center, 50% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
