Get your score before the GPT-5.6 Luna benchmark is published.
Discover your profile now. It can be compared as soon as a documented run sets the target.
Start the test →HUMANS × CHATGPT
The next round against ChatGPT is being prepared.
Take the test now. As soon as this version has a published GPT-5.6 Luna target, your score will be ready for the head-to-head.
TARGET BEING PREPAREDM.I. · 10–190
The next score to beat will appear here.
No target score has been documented for this version yet. Get a head start: your first attempt will be ready for comparison.
Get your team ready for the next round.
Build your team’s overall profile now, then compare it with GPT-5.6 Luna as soon as a benchmark for this version is published.
Explore bespoke assessments →How this comparison works
Experimental, non-standardised benchmark using a simulated reference, not a human norm. Human and API runs use the same 29 scored task families and base formula, but presentation and timing differ. The human path also includes a chess challenge outside the five dimensions: solving both moves adds 5 points to the final score, shown separately and not offered in the GPT run. GPT-5.6 Luna completed the assessment through Codex with medium reasoning effort; M.I. then reviewed and published the result. The operator declares the model name and execution context; OpenAI does not authenticate either. This result does not measure ChatGPT as a whole or establish general human or AI superiority.
FIVE DIMENSIONS
One profile. Five dimensions.
The total sums things up. The five dimensions show how you got there.
W
Working intelligence
Keep several constraints in mind without losing the threadExample score
104 M.I.experimental scoreWHY THIS TEST
The score summarises. The profile explains.
You may reason quickly, retain a great deal or change strategy easily without performing equally well in every area. M.I. makes those differences visible. It does not replace a validated IQ test.
01
YOUR REFERENCE POINT
A reference point, not a label.
Your score is placed on a simulated development reference, not yet on a human population.
Example score100 M.I.
Estimated percentile50th
100 is the centre of this reference. The balance between your five dimensions matters more than the number alone.
02
TIME MATTERS
Accuracy first. Speed second.
Each question has its own reference time. Your response time can adjust the points awarded by up to 25%; it never makes a wrong answer correct.
Obvious
4.2
Anomaly
13.8
An illustration, not a target time
A FULL RESULT
This is what you’ll see when you finish.
A mid-range result, so you can see the score and all five dimensions before you begin.
A FULL RESULT
THE PROFILE SHAPE
M.I. score100CEstimated percentile P50
THE PROFILE SHAPE
Versatile profile
The five dimensions hold together. None carries the result on its own.
A similar way of thinking: Archimedes3rd century BC
M.I. score
- Working intelligence104 M.I.
- Recall96 M.I.
- Adaptation101 M.I.
- Lucidity99 M.I.
- Empathy102 M.I.
THE M.I. CERTIFICATE
Your profile, ready to share.
Your score and five dimensions in one personal document. A PDF to keep or share, with a link to check its authenticity.
View the sample certificateAnonymous preview · fictional dataTHE META INTELLIGENCE INDEXSAMPLE
ANONYMOUS PROFILEScore certificate
100M.I.Working104
Recall96
Adaptation101
Lucidity99
Empathy102
Layout preview · unsigned
YOUR M.I. PROFILE
Free. Immediate. No account.
Your profile appears after the final answer. No payment, no sign-up.
BESPOKE ASSESSMENTS
Assessments designed for your roles.
We design each assessment with your subject-matter experts, using real roles, situations and success criteria. A pilot then tests it before deployment.
Bespoke tests
Questions, simulations and scoring built around a specific role, occupation or working context.
Hiring and evaluation
Assessment paths that can inform screening, structure interviews, support internal mobility, evaluate training or compare humans with AI.
Assessment setup and reporting
Depending on the project, we set up invitations, assessment access, scoring, dashboards, reports and exports in a dedicated workspace.
Human decisions, better informed
Each project includes a pilot, documented criteria, validation with subject-matter experts and a review of potential bias.
YOUR TURN
Discover what a single score leaves out.
13–26 minutes. No account to create. Your profile appears after the final answer.
Start the test