Skip to content
TBSI.

Start here

  • LLM LeaderboardCompare frontier models on intelligence, price and speedTool
  • What is the best superintelligence?The best frontier model for each jobModels
  • Frontier Gap ReportHow far apart the leading labs areReport
  • MethodologyHow we verify sources, data and claimsAbout

Which AI Has the Highest IQ? How Machine Intelligence Is Measured in 2026

Why AI has no real IQ score, and how GPT-6 Astra, Gemini 4 Carbon and Claude Opus 5.5 compare on reasoning benchmarks in November 2026

By TheBestSuperintelligence Editorial TeamUpdated

◈ Executive SummaryEvidence · Primary Source

Which AI has the highest IQ?

AI models do not have an official human IQ score. On reasoning benchmarks in November 2026, GPT-6 Astra leads Epoch AI's Capabilities Index (169), Gemini 4 Carbon leads the Artificial Analysis Intelligence Index (59), and Claude Opus 5.5 trails each by one point.

☰On this page (7 sections)
  1. 01.Why Standard Human IQ Tests Do Not Work on AI
  2. 02.The 2026 "Machine IQ" Leaderboard: Top Reasoning Benchmarks
  3. 03.What Drives High "AI IQ" in 2026?
  4. 04.More questions about AI and IQ
  5. 05.Which AI is smartest overall? Where to compare the models next
  6. 06.Limits of this guide
  7. 07.Sources & Further Reading

Quick Answer (TL;DR) AI models do not have an official human IQ score, because traditional IQ tests measure human psychometric traits and are easily memorized during model pre-training. Instead, researchers measure "machine IQ" using contamination-resistant reasoning and fluid-intelligence benchmarks. As of November 2026, three models trade the title of smartest AI depending on the test:

  • OpenAI GPT-6 Astra: Leads Epoch AI’s Capabilities Index (169) and sets state-of-the-art marks on ARC-AGI-3 (fluid intelligence) and FrontierMath Tier 4.
  • Google Gemini 4 Carbon: Leads the Artificial Analysis Intelligence Index (59) and arena.ai (1528 Elo).
  • Anthropic Claude Opus 5.5 / Fable 5.1: Sits one point behind the leaders on both Epoch AI (168) and Artificial Analysis (58), leading real-world autonomous computer control (OSWorld 2.1 at 81.8%).

Why Standard Human IQ Tests Do Not Work on AI

When viral charts claim a chatbot scored "140 or 155 on an IQ test," they are usually administering standardized human pattern tests (such as Raven’s Progressive Matrices or Mensa practice exams). Those numbers are misleading for two reasons:

  1. Training Data Contamination: Millions of logic puzzles, analogies, and psychometric test explanations already exist in public web scrapes used to train large language models.
  2. Spiky Cognitive Profiles: An AI model can solve PhD-level quantum mechanics problems in seconds while failing a simple novel grid puzzle that a 10-year-old solves intuitively.

To measure true reasoning power—what psychometricians call fluid intelligence—AI researchers rely on adversarial, expert-authored benchmarks.


The 2026 "Machine IQ" Leaderboard: Top Reasoning Benchmarks

Benchmark What Cognitive Skill It Measures Why It Resists Memorization Current Leader (Nov 2026)
ARC-AGI-3 Fluid Intelligence & Novel Adaptation: Solving unseen interactive environments on the fly Tasks require zero-shot abstraction in dynamic environments never seen in training OpenAI GPT-6 Astra (state-of-the-art reported)
Epoch AI Capabilities Index Composite Frontier Intelligence: Weighted synthesis of top reasoning, math, and coding evals Continuously updated across held-out, high-difficulty evaluations 1. GPT-6 Astra (169)2. Claude Opus 5.5 (168)
Artificial Analysis Index Applied Reasoning & Knowledge: Standardized multi-domain intelligence and coding suite Evaluated independently under uniform API parameters 1. Gemini 4 Carbon (59)2. Claude Opus 5.5 (58)3. GPT-6 Astra (57)
FrontierMath Tier 4 Original Mathematical Discovery: Research-level problems crafted by professional mathematicians Newly authored proofs requiring hours or days for human specialists OpenAI GPT-6 Astra
Humanity's Last Exam & GPQA Expert Academic Reasoning: 2,500+ ultra-hard questions across 100+ graduate disciplines PhD-level questions screened to defeat web search and shallow recall Claude Fable 5.1 / GPT-6 Astra / Gemini 4 Carbon
OSWorld 2.1 & Terminal-Bench 4.0 Applied Executive Function: Multi-step planning and error recovery in live software Graded by actual system state changes rather than text answers Claude Opus 5.5 (81.8% OSWorld / 66.4% Terminal-Bench)

Note: both Anthropic (66.4% for Claude Opus 5.5) and OpenAI (state of the art for GPT-6 Astra) report leading Terminal-Bench 4.0 results. Both are vendor-reported, on settings each vendor chose.


What Drives High "AI IQ" in 2026?

The leap in reasoning scores across 2025–2026 comes from test-time compute scaling (also called "thinking effort"). Rather than emitting the first plausible word immediately, frontier models like Claude Opus 5.5, GPT-6 Astra, and Gemini 4 Carbon generate internal chains of thought—testing hypotheses, catching logical contradictions, running code interpreters to verify calculations, and backtracking before delivering a final answer.

More questions about AI and IQ

Why do standard human IQ tests fail to measure AI intelligence?

Standard human IQ tests suffer from training data contamination and fail to capture the spiky cognitive profile of AI models, which can solve PhD-level science problems while struggling on simple novel spatial puzzles.

Which AI is smartest overall? Where to compare the models next

Limits of this guide

Benchmark positions change every few weeks; scores were read between October 27 and November 3, 2026. Several results are vendor-reported. No benchmark is an IQ test.

Sources & Further Reading

Claim Source Date
Epoch Capabilities Index: Astra 169, Opus 5.5 168 Epoch AI ECI Downloaded 2026-11-03
Artificial Analysis Intelligence Index: Carbon 59, Opus 5.5 58, Astra 57 Artificial Analysis Viewed 2026-11-03
arena.ai text leaderboard: Carbon 1528 (preliminary), Argon 1520, Opus 5.5 1509; six Anthropic models in top ten arena.ai text leaderboard Updated 2026-10-27
Vendor-reported scores: Opus 5.5 66.4% Terminal-Bench 4.0 and 81.8% OSWorld 2.1; Astra state of the art on FrontierMath Tier 4, ARC-AGI 3 and Terminal-Bench 4.0; Argon 77.9% DeepSWE v1.1; Carbon 88.2% SEC-bench Pro Anthropic: Claude Opus 5.5; OpenAI: GPT-6 Astra; Google: Gemini 4 Carbon Read 2026-11-03
Humanity's Last Exam: 2,500 questions across more than a hundred subjects Humanity's Last Exam Read 2026-10-07
ARC-AGI-3 interactive benchmark ARC Prize Read 2026-10-07
Model lineups, release dates and context windows Anthropic models overview; OpenAI: GPT-6 Astra; Gemini API changelog Re-checked 2026-11-03

Frequently asked questions

Which AI has the highest IQ?

AI models do not have an official human IQ score. On reasoning benchmarks in November 2026, GPT-6 Astra leads Epoch AI's Capabilities Index (169), Gemini 4 Carbon leads the Artificial Analysis Intelligence Index (59), and Claude Opus 5.5 trails each by one point.

What is the highest IQ ever recorded for an AI?

AI systems do not receive valid human IQ scores. While frontier models routinely score above 130–145 on unverified online IQ quizzes, researchers evaluate true machine intelligence using ARC-AGI-3, FrontierMath, and Epoch AI’s Capabilities Index, where GPT-6 Astra (169) and Claude Opus 5.5 (168) lead in November 2026.

Which AI is smartest for math and science?

OpenAI’s GPT-6 Astra and Anthropic’s Claude Fable 5.1 lead graduate-level mathematics and scientific reasoning benchmarks, with Astra reporting state-of-the-art results on FrontierMath Tier 4.

Does higher reasoning ability mean fewer hallucinations?

Higher reasoning effort significantly reduces logical and mathematical errors because the model checks its own intermediate steps, though no model is completely immune to hallucinations without external grounding and verification.

Which AI has the highest IQ in 2026?

AI models do not possess valid human IQ scores. On scientific fluid-intelligence and reasoning benchmarks in November 2026, OpenAI's GPT-6 Astra leads Epoch AI's Capabilities Index (169) and ARC-AGI-3, while Google's Gemini 4 Carbon leads the Artificial Analysis Intelligence Index (59) just ahead of Anthropic's Claude Opus 5.5 (58).

How we sourced this. Text supplied by the site owner. Scores and dates were cross-checked against the dated sources below; items we could not confirm are flagged on the page. Methodology