OpenAI’s GPT-4 tops Mensa Norway IQ test chart
OpenAI’s GPT-4 leads the pack in IQ scores among 24 top AI models tested on the Mensa Norway IQ test. The AI heavyweight scored highest, putting it ahead of competitors like Anthropic’s Claude, Google Bard, and Meta’s LLaMA.
The test ranks AI models based on reasoning, pattern recognition, and problem-solving. GPT-4 scored well above most others, showcasing its sharp performance across IQ indicators. 
This infographic from Visual Capitalist lays out the IQ scores for each AI, comparing their cognitive horsepower straight-up.
AI IQ rankings like this give a snapshot of how different models stack up on standardized intelligence metrics. GPT-4’s reign here adds fuel to debates over AI capabilities and benchmarks.
Stay tuned as the contest between AI brainpower continues to heat up.
