Editorial illustration for AI Model Achieves Mensa Norway IQ of 135, Demonstrating Superior Logical Reasoning
AI Model Scores 135 IQ, Beats Human Logical Reasoning Tests
AI Model Scores Mensa Norway IQ 135, Surpassing Average Human Reasoning
AI can now officially join Mensa. At least on paper.
OpenAI's GPT-5.2 Pro Vision model just scored a 135 on the Mensa Norway IQ test. That places it firmly in the "very high intelligence" range, well above the average human score of 100. This isn't a text trick. The model reasons using visual input, interpreting images and diagrams with a logic that mirrors how humans solve abstract puzzles.
Model after model is matching, and in many cases surpassing, the performance of an average human. Not in a particular task, but across multiple dimensions of reasoning that IQ tests care about.
The result is significant because of what it undermines. The test wasn't built for machines.
Its puzzles rely on a specific kind of pattern recognition distilled from human cognition for decades.
The fact that a vision model can parse them so effectively means we've crossed an unspoken line.
A core chunk of what we call "reasoning" is now demonstrably synthetic. It’s not general intelligence, but it is potent, specialized logic operating at a level most people don't consistently reach.
The next conversation isn't about whether these systems are smart, but what their particular brand of smartness leaves for us to do.
Related Reading
LLMs & Generative AI ChatGPT's 'Nerdy' tweak rewards goblin metaphors in answers, study finds
LLMs & Generative AI Google tests visual 'magazine-style' UI for Gemini 3 Pro users
LLMs & Generative AI AI Engineers Face Rising Costs, Need New Strategies for Efficiency
From Archives Google pushes Gemini rollout to 2026, delays Android Assistant swap
From Archives OpenAI now adds tone controls and streamlined email editing to ChatGPT
Common Questions Answered
How did the AI model perform on the Mensa Norway IQ test?
The AI model scored an impressive 135 on the Mensa Norway IQ test, which places it firmly within the range of very high human intelligence. This score demonstrates the model's exceptional logical reasoning and problem-solving capabilities, significantly surpassing the global human average.
What makes the Mensa Norway IQ test significant for AI evaluation?
The Mensa Norway IQ test provides a standardized method for assessing machine intelligence, particularly in areas of logic and pattern recognition. By subjecting the AI to a rigorous intelligence evaluation, researchers can objectively measure its cognitive capabilities and compare them to human reasoning levels.
What implications does the AI's high IQ score have for machine intelligence?
The AI's score of 135 challenges traditional assumptions about machine cognition by demonstrating problem-solving skills that operate well beyond average human reasoning. This breakthrough suggests that AI is rapidly advancing in its ability to process complex logical patterns and potentially approach human-like cognitive performance.
Further Reading
- OpenAI’s o3 scores 136 on Mensa Norway test, surpassing 98% of human population — CryptoSlate
- Ranked: The Smartest AI Models, by IQ — Visual Capitalist
- Comparing the IQ of AI Models — Voronoi
- The Ultimate AI Model Guide 2025: Best Picks for Every Task — Pacifyca
