¡Test the IQ of your favorite AI model! ...it's my MeMe #315
«2026 Stats»
As of early 2026, leading AI models have demonstrated exceptional performance on the Mensa Norway online IQ test, with top models achieving scores well into the "genius" range ((>130)). The test, which consists of 35 matrix-style puzzles, has become a key benchmark for measuring AI reasoning and pattern recognition.
But before you go any further, please test your own IQ first!
¡Test Your OWN IQ!
And if you are really curious, here below my own IQ test results. 
Posts with rewards set to burn still pay curators.
Only author rewards are burned.
If you think this type of content should be eligible for author rewards, then «click» here.
Thanks for your support.
«Test the IQ of your favorite AI»
Key Findings on AI Mensa Norway Scores (2025–2026)
Top Performers (2026): According to TrackingAI's April 2026 benchmark, models like OpenAI GPT-5.4 Pro and Grok-4.20 Expert Mode have hit scores of 145–150 on the test.
Rapid Growth: AI performance on this test has increased exponentially. In early 2025, models scored around 117; by April 2025, OpenAI's o3 reached 136, exceeding the top 2% threshold for human Mensa entry.
Offline/Contamination Check: While some argue AI excels due to training data contamination, top models still scored 116 on an "offline" version of the test, confirming high-level reasoning capabilities.
Pattern-Recognition Focus: The test is highly visual, relying on 35 progressive matrix patterns. Because AI is trained specifically for pattern recognition, these tests are highly optimized for them.
Performance Comparison (Approximate)
Average Human: IQ 100
Mensa Norway Entry Threshold: Approx. IQ 132–135
GPT-4 (2024): ~85–96 IQ
OpenAI o3 (April 2025): 136 IQ
GPT-5.4 Pro/Grok-4.20 (April 2026): 145–150 IQ
While these scores actually demonstrate incredible pattern recognition in the AI models tested so far, they do not necessarily equate to human-like general intelligence, as LLMs indeed can often solve visual puzzles better through specialized training.
Then, ¿are you just average or are you smarter than your favorite AI model?
«««-$-»»»
"Follows, Comments, Rehives & Upvotes will be highly appreciated"
Fascinating. I never did an IQ test... I don't want to know my score. If its too low then I will assume that I'm a slave of my limited intelligence. If it's high then I will judge myself for not living up to a higher potential. The result might be a lose-lose for me.
So this is interesting (not sure I understand why)... ChatGPT 4.5 IQ is 145 at visual puzzle solving, but when it comes to verbal problem solving it is the lowest?
Ah, don't worry babe. Just do it quickly, like I had to do it to publish this post in the shortest time possible. LoL
Well, then to me, your way of thinking denotes a very high IQ, if anyone asks me. Because Real Life Stuff isn't deciphered solely through geometric figures, you know?
Yeah, that's correct. This could be understood more easily with the following example:
Just like humans, some of us are more visual and others are more auditory. The former use the right hemisphere of their brain more and have already realized it. Therefore, they tend to train and develop it more than the other hemisphere. And as result, they develop a greater ability to interpret abstractly geometric figures and process information holistically, intuitively, and visually, which is fundamental for creativity, emotional expression, music, and spatial orientation.
On the other hand, those who are more auditory tend to use their left brain hemisphere much more than their right. And they've already realized that too. Therefore, they tend to train it more in logical activities of sequential analysis and rational thinking where language skills are the star product of that training and consequently more skilled when it comes to processing and managing cognitive functions such as mathematical calculation, writing and reading.
As you can see, it all depends on the training we/they have given to our/their brain. Hence, there are some of us who stand out at visual puzzle solving but get poor scores at verbal problem solving and vice-versa.
Makes a lot of sense - it's a question of training.
Thanks, and yes very true, there are other forms of intelligence that are also vital for our wellbeing, IQ is not end-all-be-all
LOL, maybe 😜
I avoid ai. I know they all are programmed to lie about certain things - like whether We have free energy tech.
I know We have it, and all ai's will say otherwise.
The ai's serve the moneyed psychopaths in control on Our planet (by virtue of money).