Top all-time · #5398
Maxim Lott
Personal blog · maximumtruth.orgaidata
Maxim Lott writes Maximum Truth, a personal blog at maximumtruth.org about ai and data. Since 2024, 14 different Hacker News readers have linked it 16 times, most often “Breakthrough in AI intelligence: OpenAI passes IQ 120”. It is still writing: the last post was on 2025-12-31, and you can follow it by feed.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
Maxim Lott's blog publishes IQ-test results for AI models and compares them with human scores. HN threads on AI intelligence and benchmarks link it, including a Mensa-test ranking of frontier models.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Join me on a data-driven search for the truth!
Most-linked posts?
- Breakthrough in AI intelligence: OpenAI passes IQ 1205 people · 6 mentions · first linked 2024-09-14
- AIs ranked by IQ; AI passes 100 IQ for first time, with release of Claude-33 people · 4 mentions · first linked 2024-03-05
What Hacker News says?
This claim that these tests are easy for humans seems dubious, and so I went looking a bit. Melanie Mitchell chimed in on Chollet's thread and posted their related test [ConceptARC]. In it they question the ease of Chollet's tests: "One limitation on ARC’s usefulness for AI research is that it might be too challenging. Many of the tasks in Chollet’s corpus are difficult even for humans, and the corpus as a whole mig…
Comment linking /p/ais-ranked-by-iq-ai-passes-100-iq
on “ARC Prize – a $1M+ competition towards open AGI progress”Submitted Top AIs still fail IQ tests as a story · 49 points
HN discussionFor a while, I have been making use of Clever Hans as a metaphor. The horse seemed smarter than it really was. They can certainly appear to be very smart due to having the subjective (if you can call it that) experience of 2.5 million years of non-stop reading. That's interesting, useful, and is both an economic and potential security risk all by itself. But people keep putting these things through IQ tests; as ther…
Comment linking /p/massive-breakthrough-in-ai-intelligence
on “Microsoft and OpenAI's close partnership shows signs of fraying”Submitted AIs ranked by IQ; AI passes 100 IQ for first time, with release of Claude-3 as a story · 31 points
HN discussionI agree that it's wrong to do so, but the maintainer of this site certainly thinks that the point is to compare humans with AI. He frequently compares the results to human IQ test takers without any sort of caveats: "Now o3 scores an IQ of 116, putting it in the top 15% of humans. The median Maximum Truth reader, for comparison, scored 104." [0] 0: https://www.maximumtruth.org/p/skyrocketing-ai-intelligence-...
Comment linking /p/skyrocketing-ai-intelligence-chatgpts
on “IQ tests results for AI”Submitted Breakthrough in AI intelligence: OpenAI passes IQ 120 as a story · 13 points
HN discussionAgreed on the first part, but for LLMs not having correlated capabilities, I think we've seen they do. As the GPTs progress, mainly by model size, their scores across a battery of tests goes up, eg OpenAI's paper for ChatGPT 4, showing a leap in performance across a couple dozen tests. Also found this, a Mensa test for across the top dozen frontier models. https://www.maximumtruth.org/p/ais-ranked-by-iq-ai-passes-10…
Comment linking /p/ais-ranked-by-iq-ai-passes-100-iq
on “Transformers Can Do Arithmetic with the Right Embeddings”Submitted Deep DIVE: AI progress continues, as IQ scores rise linearly as a story · 5 points
HN discussionIt's both. I recently saw a comparison of various models on two IQ tests, one of which was public and the other of which was carefully curated to be not directly learnable from the likely training sets. On public tests, LLMs vary between "just below average human" and "genius". On the hopefully-private test (it's difficult to be sure*), the best was o1, which was "merely" just below an average human, Claude-3 Opus w…
Comment linking /p/massive-breakthrough-in-ai-intelligence
on “If AI seems smarter, it's thanks to smarter human trainers”Submitted OpenAI's new "o1" model may have an IQ as high as 120 as a story · 5 points
HN discussionSubmitted AI passes 100 IQ (Claude 3) as a story · 5 points
HN discussionSubmitted Breakthrough in AI intelligence: OpenAI passes IQ 120 as a story · 3 points
HN discussionSubmitted DeepSeek is NOT as smart as o1 on unseen IQ questions as a story · 2 points
HN discussionSubmitted Tracking AI bias with political compass as a story · 2 points
HN discussionSubmitted Does OpenAI's o1 have an IQ of 120? as a story · 2 points
HN discussionSubmitted AI IQ scores (mostly) confirmed, using new offline IQ test as a story · 2 points
HN discussion
