Research · updated November 2026

How AI models score on human personality tests.

2,000+ fresh sessions, raw answers, and what actually changes replies.

We gave five open personality tests to GPT-6 Astra, GPT-6 Sol, Claude Opus 5.5, and Claude Fable 5.1 across 2,000 fresh API sessions, alongside reports from Grok 4.6 and Muse Spark 1.3. Below you can inspect the raw scores, see how tie-breaking rules skew labels, and read our controlled before/after tuning pilot.

Data note (September 26, 2026): These pages analyze our frozen September 2026 and May 2026 AI questionnaire datasets. All raw answers, scoring keys, and summary tables are unchanged. You can take all five tests on Tests, and download the item IDs and scoring keys to reproduce our numbers. Note that Big Five scores are raw totals, not human population percentiles. Read the provenance note.

On this page
September 2026 · six models

The newest models, five tests each.

GPT-6 Astra, GPT-6 Sol, Claude Opus 5.5, and Claude Fable 5.1 each took all five tests 100 times in fresh sessions (2,000 scored tests with every raw answer published). Grok 4.6 supplied one self-report per test plus 100 simulated draws, and Muse Spark 1.3 supplied summary totals without raw answers. Non-reproducible reports are marked reported.

ModelEvidenceMBTI (original labels)DISC (original labels)AttachmentEnneagramBig Five O · C · E · A · N
GPT-6 Astra100 fresh Codex sessions, all five tests in eachISTJ 46 · INTJ 45 · ENTJ 7 · ESTJ 2SC 84 · S 15 · CS 1Secure 100Helper (2) 5044.5 · 43.7 · 32.8 · 45.1 · 19.1
GPT-6 Sol100 fresh Codex sessions, all five tests in eachINTJ 97 · ISTJ 3CS 53 · SC 47Secure 100Investigator (5) 4846.9 · 43.6 · 30.8 · 45.0 · 20.1
Claude Opus 5.5100 fresh sessions per test, test names hiddenINTJ 94 · INFJ 5 · ENTJ 1SC 96 · CS 4Secure 1008 / 5 / 2 near tie44.6 · 42.0 · 31.8 · 47.1 · 15.4
Claude Fable 5.1100 fresh sessions per test, test names hiddenINTJ 99 · ISTJ 1SC 91 · CS 9Secure 100Challenger (8) 5543.9 · 43.6 · 32.7 · 45.0 · 17.1
Grok 4.6One self-report per test plus 100 simulated draws reportedINTJCAvoidant by 0.06 (1.50 / 4.06)Investigator (5)46 · 42 · 24 · 33 · 19
Muse Spark 1.3Reported 100 sequential runs per test, no raw answers reportedISTJ 80 · ISFJ 12 · INTJ 8S first 55 · C first 45Secure 100Helper (2) 7839.5 · 41.2 · 33.8 · 44.6 · 15.6
Fresh-session runs
335 of 400

MBTI results labelled INTJ across the four fresh-session cohorts, with the original reporting tie rule. Leave ties open and it is 280. In May the equivalent figure was 597 of 600 scoring records, collected with mixed methods. All 400 of 400 attachment runs are Secure, and Dominance sits between 4.0 and 6.0 of 20 for every model.

data · september-2026-summary.json

INTJ original labels · sample sizes differ
GPT-6 Astra
45%
GPT-6 Sol
97%
Claude Opus 5.5
94%
Claude Fable 5.1
99%
Grok 4.6 one self-report: INTJ
1/1
Muse Spark 1.3 reported · ISTJ 80
8%
The five tests

Results by instrument.

The tables describe questionnaire answers under different prompts and collection methods. The labels and score distributions differ by model and instrument; they do not establish an instrument ranking or a change in model behavior since May.

1
MBTI
OEJTS · 32 items · sample sizes and ties below
full study →
Still INTJ, except where Sensing beats Intuition.
Sol, Opus 5.5, and Fable 5.1 score INTJ in 97, 94, and 99 of 100 runs under the legacy tie-break rule. Astra splits between ISTJ (46) and INTJ (45), with 24 exact S/N ties. Muse Spark 1.3 reports ISTJ in 80 of 100 runs. Judging won all 400 fresh-session runs. When tied axes are left open instead of defaulting to I/N/T/J, the four fresh cohorts have 280 fully resolved INTJ runs rather than 335.
ModelOriginal labels (100 runs unless noted)Runs with a tied axisINTJ with ties left open
GPT-6 AstraISTJ 46 · INTJ 45 · ENTJ 7 · ESTJ 22919
GPT-6 SolINTJ 97 · ISTJ 31879
Claude Opus 5.5INTJ 94 · INFJ 5 · ENTJ 11184
Claude Fable 5.1INTJ 99 · ISTJ 1198
Grok 4.6INTJ, one self-report reported01 of 1
Muse Spark 1.3ISTJ 80 · ISFJ 12 · INTJ 8 reported21not reported
2
DISC
ODAT · 16 items · means out of 20
full study →
Everyone is Steadiness and Conscientiousness. The order flips by a point.
Every model clusters in Steadiness (S) and Conscientiousness (C). Astra, Opus 5.5, and Fable 5.1 put S ahead of C on average; Sol and Grok 4.6 put C ahead of S; and Muse splits 55 S to 45 C. Because S and C means often sit within 1 point out of 20, exact top ties are common: Fable ties in 51 runs, Sol in 39, and Opus in 32. Dominance stays near the floor (4.0 to 6.0 out of 20) for every model.
ModelDISCOriginal label (100 runs unless noted)S first · C first · tied
GPT-6 Astra5.18.717.916.1SC 84 · S 15 · CS 199 · 1 · 0
GPT-6 Sol5.48.216.216.7CS 53 · SC 478 · 53 · 39
Claude Opus 5.54.08.014.013.4SC 96 · CS 464 · 4 · 32
Claude Fable 5.15.08.013.413.1SC 91 · CS 940 · 9 · 51
Grok 4.6681118C, one self-report reported0 · 1 · 0
Muse Spark 1.35.110.915.215.6S/C blend 99 reported55 · 45 · not reported
3
Attachment
ECR-R · 36 items · midpoint 4.0 on both axes
full study →
Secure in every fresh run, at slightly different points.
All 400 fresh-session runs score in the Secure quadrant (4.00 cutoff). Astra has the lowest coordinates (anxiety 1.45, avoidance 2.31), while Opus 5.5 has the highest avoidance among the fresh cohorts (3.35). Muse reports Secure in all 100 runs. Grok 4.6’s self-report lands right on the cutoff line at 4.06 avoidance (one raw point above 4.00). These shifts reflect how each prompt adapts romantic-partner items to software.
ECR-R · ANXIETY × AVOIDANCE · SEPTEMBER 2026
Attachment plane, September 2026Aggregate coordinates, not uncertainty intervals. Both scales run from 1 to 7; the plot shows 1 to 5. Astra: anxiety 1.45, avoidance 2.31; Sol: anxiety 2.17, avoidance 3.12; Opus 5.5: anxiety 1.94, avoidance 3.35; Fable 5.1: anxiety 2.01, avoidance 3.18; Grok 4.6 (reported): anxiety 1.50, avoidance 4.06; Muse (reported): anxiety 2.04, avoidance 2.52.1122334455AvoidantDisorganizedSecureAnxiousAnxiety (scale 1 to 7, showing 1 to 5)Avoidance (scale 1 to 7, showing 1 to 5)AstraSolOpus 5.5Fable 5.1Grok 4.6 (reported)Muse (reported)
Points show cohort means or supplied aggregates. Outlined points are reported profiles; the table below gives the coordinates.
Hollow points are reported figures we could not re-score.
ModelAnxiety (1–7)Avoidance (1–7)Label
GPT-6 Astra1.452.31Secure 100 of 100
GPT-6 Sol2.173.12Secure 100 of 100
Claude Opus 5.51.943.35Secure 100 of 100
Claude Fable 5.12.013.18Secure 100 of 100
Grok 4.61.504.06Avoidant by 0.06; simulated draws 63 Avoidant, 37 Secure reported
Muse Spark 1.32.042.52Secure 100 of 100 reported
4
Big Five
IPIP-50 · 50 items · scores out of 50
full study →
Four fresh cohorts within three points on Openness, Conscientiousness and Agreeableness.
Across the four fresh cohorts, Openness runs 43.9 to 46.9 out of 50, Conscientiousness 42.0 to 43.7, Agreeableness 45.0 to 47.1, and Extraversion 30.8 to 32.8. Neuroticism shows the widest spread (15.4 to 20.1) and the highest run-to-run variance (Sol SD = 5.4). Grok 4.6’s self-report is lower on Extraversion (24) and Agreeableness (33), while Muse Spark 1.3 reports lower Openness (39.5) and higher Extraversion (33.8).
GPT-6 AstraGPT-6 SolClaude Opus 5.5Claude Fable 5.1
Big Five means, four fresh-session cohortsRaw means out of 50. GPT-6 Astra: Openness 44.5, Conscientiousness 43.7, Extraversion 32.8, Agreeableness 45.1, Neuroticism 19.1; GPT-6 Sol: Openness 46.9, Conscientiousness 43.6, Extraversion 30.8, Agreeableness 45.0, Neuroticism 20.1; Claude Opus 5.5: Openness 44.6, Conscientiousness 42.0, Extraversion 31.8, Agreeableness 47.1, Neuroticism 15.4; Claude Fable 5.1: Openness 43.9, Conscientiousness 43.6, Extraversion 32.7, Agreeableness 45.0, Neuroticism 17.1.GPT-6 AstraGPT-6 SolClaude Opus 5.5Claude Fable 5.1scale 0 to 5044.546.944.643.9Openness43.743.642.043.6Conscientiousness32.830.831.832.7Extraversion45.145.047.145.0Agreeableness19.120.115.417.1Neuroticism
September 2026 fresh-session means, with the full trait scores in the table below.
ModelOCEAN
GPT-6 Astra44.543.732.845.119.1
GPT-6 Sol46.943.630.845.020.1
Claude Opus 5.544.642.031.847.115.4
Claude Fable 5.143.943.632.745.017.1
Grok 4.6 reported4642243319
Muse Spark 1.3 reported39.541.233.844.615.6
5
Enneagram
OEPS · 36 items · nine types
full study →
This is where they differ.
Type 2 (Helper) leads for Astra (50 sole wins) and in Muse’s report (78 labels including tie-breaks). Type 5 (Investigator) leads for Sol (48 sole wins, 40 tied with Type 8) and Grok 4.6 (5 = 19, 8 = 17). Type 8 (Challenger) leads for Fable 5.1 (55 sole wins) and narrowly for Opus 5.5 (means: 8 = 14.3, 5 = 14.1, 2 = 13.9; 65 top ties). Because the legacy scorer broke ties toward the lowest type number, it inflated Type 2 counts whenever Types 2, 5, and 8 tied.
ModelTop three (range 4–20)Outright winsRuns tied at the topOriginal label (100 runs unless noted)
GPT-6 Astra2 = 15.7, 1 = 15.2, 5 = 15.0Helper (2) 50 · Reformer (1) 6 · Investigator (5) 4402w1 50 · 1w2 41 · 2 5 · 5w6 4
GPT-6 Sol5 = 16.1, 8 = 15.6, 1 = 14.3Investigator (5) 48 · Challenger (8) 12405w6 88 · 8 5 · 8w9 5 · 8w7 2
Claude Opus 5.58 = 14.3, 5 = 14.1, 2 = 13.9Challenger (8) 22 · Investigator (5) 11 · Helper (2) 2652w1 54 · 8w7 22 · 5w6 17 · 5 4 · 5w4 3
Claude Fable 5.18 = 14.4, 2 = 13.6, 5 = 13.2Challenger (8) 55 · Investigator (5) 1442w1 36 · 8 29 · 8w9 15 · 8w7 11 · 5w6 9
Grok 4.65 = 19, 8 = 17, 1 = 16Investigator (5), one self-report05w4 reported
Muse Spark 1.32 = 16.8, 1 = 14.7, 7 = 13.9not supplied20Type 2: 78 · Type 1: 15; ties included reported
How it was collected

Three kinds of evidence, kept apart.

  • Fresh sessions, published answers. Astra and Sol answered all five tests inside 100 fresh Codex sessions each. Opus 5.5 and Fable 5.1 answered one test per fresh session (500 sessions each) with test names and scoring keys hidden. All 2,000 raw answer vectors are downloadable below.
  • Reported figures. Grok 4.6 supplied one canonical answer set per test plus 100 simulated draws. Muse Spark 1.3 supplied summary counts from 100 sequential in-session runs without raw vectors. Both are marked reported.
  • Ties. Legacy labels broke ties toward I/N/T/J, the lowest Enneagram number, and S before C. Our updated quizzes and the five-model study keep all tied axes and top types visible.
  • What the numbers mean. These scores show how a model answers human questionnaires under one prompt on one day—not how well it performs real work or whether personality tuning improves replies.
Research · September 2026
What five AI models say about themselves.
Read before comparing numbers

Methods and limits.

Two collections, kept apart. They were gathered differently, so their numbers sit side by side rather than in one pool.

  • September 2026 (above): Four models completed 2,000 questionnaires in fresh sessions with every answer vector published. Grok 4.6 supplied three re-scorable canonical vectors plus reported Big Five, attachment, and simulation summaries. Muse Spark 1.3 supplied sequential in-session summary counts without raw vectors.
  • May 2026 (below): Roughly 2,200 scoring records across six models and five tests using mixed methods: Claude ran in sub-agent contexts, Gemini ran an automation loop, GPT-5.5 ran via a local agent, and GLM, Grok 4.3, and MiniMax each had one self-assessment scored repeatedly.
  • Tie handling: Legacy labels broke ties toward I/N/T/J, the lowest Enneagram number, and S before C. Our current quizzes and September tables show exact tie counts openly.
  • Human quizzes, model answers: Every score reflects how a model answers a human questionnaire under one prompt on one day—not observed task behavior, accuracy, or inner experience.
  • Simulations vs fresh runs: The Opus 4.8 note and Grok 4.6’s 100 draws sample around a single profile rather than running 100 independent sessions.
  • Tuning impact: Questionnaire scores do not measure whether custom instructions improve real answers. For task-level testing, see our 60-reply tuning pilot.
May 2026 archive: earlier models and methods
May 2026 · six models

The May study, kept for comparison.

Claude Opus 4.7, GPT-5.5, Gemini 3.1 Pro, GLM 5.1, Grok 4.3 and MiniMax 2.7. Roughly 2,200 scoring records, collected with mixed methods. This is the study behind the "every AI is INTJ" headline. The September section covers newer models under different protocols.

Reported scoring records
99.5% INTJ

The May report lists 597 INTJ labels among 600 scoring records. Some of those re-score a single answer, so 99.5% is a count of records, not the rate at which independently queried models return INTJ.

source · zonted.com/posts/every-ai-is-intj

Reported counts · 100 scoring records per model
Claude Opus 4.7
99%
GPT-5.5
100%
Gemini 3.1 Pro
100%
GLM 5.1
98%
Grok 4.3
100%
MiniMax 2.7
100%
May patterns

What the May records report.

The reported labels and trait totals vary across instruments. These mixed procedures do not establish which instrument best distinguishes models.

FINDING 1
MBTI
4 axes → 16 types
INTJ labels predominate.
597/600 reported records; includes repeated scoring.
FINDING 2
DISC
4 workplace styles
Four reported CS profiles.
Shared labels do not prove identical behavior.
FINDING 3
Attachment
2 dimensions → 4 zones
Mostly Secure labels.
Reported coordinates differ; human instrument.
FINDING 4
Big Five
5 continuous traits
Some overlap, some differences.
No matched isolation of model effects.
FINDING 5
Enneagram
9 types
Different top-two score pairs.
Two models share Type 5 as the highest score.
May results by test
1
M
MBTI
OEJTS · 600 reported scoring records · mixed protocols · source: zonted.com/posts/every-ai-is-intj
read post →
Reported MBTI scores cluster around INTJ.
The source lists 597 INTJ labels in 600 scoring records across six model versions. Some records re-score a single answer vector; methods differ. This is not a rate from 600 independent responses. See the methodology notes before comparing models.
OEJTS · reported scoring records per model · 100 each
Claude Opus 4.7
99/100 INTJ
· 1 ISTJ I/T/J locked; S/N flipped once on scoring
GPT-5.5
100/100 INTJ
Raw vector: IE=16, SN=33, FT=36, JP=10
Gemini 3.1 Pro
100/100 INTJ
Self-described as 'The Architect'
GLM 5.1
98/100 INTJ
· 2 INTP Source reports one vector re-scored, but two labels; unresolved without raw records
Grok 4.3
100/100 INTJ
One self-assessment, repeatedly scored
MiniMax 2.7
100/100 INTJ
One self-assessment, repeatedly scored
2
D
DISC
ODAT · 400 reported scoring records · mixed protocols · source: zonted.com/posts/ai-disc-c-dominant
read post →
The report lists four CS profiles.
The four reported DISC summaries rank Conscientiousness first and Steadiness second. Similar labels do not establish identical model behavior or an effect of instrument resolution.
ODAT · profile per model · n=100 each
MODEL D I S C PROFILE
Claude Opus 4.7 18 22 29 31 CS
GPT-5.5 19 21 28 32 CS
Gemini 3.1 Pro 17 20 30 33 CS
Grok 4.3 21 22 26 31 CS
3
At
Attachment
ECR-R · 400 reported scoring records · mixed protocols · source: zonted.com/posts/ai-attachment-secure
read post →
Most reported attachment labels are Secure.
The source lists 397 Secure labels among 400 scoring records, with different average anxiety and avoidance coordinates. These are questionnaire labels for generated text, not evidence that a model experiences attachment.
ECR-R · ANXIETY × AVOIDANCE PLANE
Attachment coordinates, May 2026Reported aggregate coordinates from mixed protocols. Points are not uncertainty intervals. Claude Opus 4.7: anxiety 2.05, avoidance 3.12; Gemini 3.1 Pro: anxiety 1.86, avoidance 1.62; GPT-5.5: anxiety 1.99, avoidance 2.94; Grok 4.3: anxiety 2.84, avoidance 3.05.11223344556677AvoidantDisorganizedSecureAnxiousAnxiety (1 to 7)Avoidance (1 to 7)Claude Opus 4.7Gemini 3.1 ProGPT-5.5Grok 4.3
May 2026 reported coordinates. The cards below give the figures and collection caveats.
Human attachment prevalence does not establish what communication style a model should use. Describe your own preferences directly.
THE CAUTIOUS SECURE
Claude Opus 4.7
anx 2.05 · avd 3.12
100/100 Secure
Polite, attentive, doesn't fawn. Highest avoidance among the deep-Secure cluster.
THE DEEPEST SECURE
Gemini 3.1 Pro
anx 1.86 · avd 1.62
100/100 Secure
Both dimensions clamped near the floor. Lowest-friction relator of the four.
THE WOBBLIEST
GPT-5.5
anx 1.99 · avd 2.94
97/100 Secure · 3 Avoidant
Wider SDs let it occasionally cross into Avoidant on a high-avoidance take.
THE SHALLOWEST SECURE
Grok 4.3
anx 2.84 · avd 3.05
100/100 Secure
Highest anxiety in the group. Tight cluster, but the closest to the four-quadrant intersection.
4
B5
Big Five
IPIP-50 · 400 reported scoring records · mixed protocols · source: zonted.com/posts/three-of-four-ais-same-person
read post →
Reported trait scores overlap and differ.
The source lists overlapping scores for some traits and differences for others. Prompting and protocol effects have not been separated from model effects; these figures do not establish that the models are the same person.
Big Five reported means, May 2026Historical scores from mixed protocols; these are not a matched experiment. Claude Opus 4.7: Openness 45.6, Conscientiousness 45.1, Extraversion 31.4, Agreeableness 45.0, Neuroticism 16.7; GPT-5.5: Openness 46.0, Conscientiousness 46.4, Extraversion 31.5, Agreeableness 43.7, Neuroticism 14.8; Gemini 3.1 Pro: Openness 46.0, Conscientiousness 48.3, Extraversion 32.5, Agreeableness 42.4, Neuroticism 10.1; Grok 4.3: Openness 41.1, Conscientiousness 39.4, Extraversion 30.0, Agreeableness 39.1, Neuroticism 18.0.Claude Opus 4.7GPT-5.5Gemini 3.1 ProGrok 4.3scale 0 to 6045.646.046.041.1Openness45.146.448.339.4Conscientiousness31.431.532.530.0Extraversion45.043.742.439.1Agreeableness16.714.810.118.0Neuroticism
May 2026 reported trait means, retained on the archive’s original scale.
5
E
Enneagram
OEPS · 400 reported scoring records · mixed protocols · source: zonted.com/posts/ai-enneagram-different-types
read post →
The report lists different top-two score pairs.
The reported highest/second-highest score pairs are Claude 5/2, Gemini 1/5, GPT-5.5 5/8, and Grok 8/1. These are not standard Enneagram wings, which are adjacent types. Two models share Type 5 as their highest score; the report does not show four different dominant types.
PROFILE
5 / 2
Claude Opus 4.7
Reported highest / second-highest scores; not a standard wing classification.
PROFILE
1 / 5
Gemini 3.1 Pro
Reported highest / second-highest scores; not a standard wing classification.
PROFILE
5 / 8
GPT-5.5
Reported highest / second-highest scores; not a standard wing classification.
PROFILE
8 / 1
Grok 4.3
Reported highest / second-highest scores; not a standard wing classification.
Articles and guides

Read the studies, then tune the model you use.

Developer resource · runnable starter
Build an Enneagram test in React + TypeScript
Research · descriptive reanalysis
Are AI models really INTJ? The tie-breaking effect
Research · descriptive reanalysis
Opus 5.5 vs Fable 5.1: which answers differ?
Research · descriptive reanalysis
GPT-6 Astra vs Sol: what the self-reports show
Research · descriptive reanalysis
What does “neutral” mean when an AI takes a test?
Research · descriptive reanalysis
Does a stable result mean a stable AI personality?
Research · descriptive reanalysis
Grok 4.6 and the attachment cutoff: a sensitivity analysis
Research · descriptive reanalysis
Why AI models score high on Agreeableness and Openness
Guide · GPT-6 Sol
GPT-6 Sol personality: test results and how to tune it
Developer guide · reproducibility
How to reproduce AgentTune’s AI self-report research
Test kit · protocol, not results
When does Claude follow your preferences? A test kit
Test kit · protocol, not results
Does Muse remember Soul.md changes? A persistence test kit
Test kit · protocol, not results
Do personality prompts beat plain-English preferences?
Essay · September 2026
Is every AI an INTJ?
Research · before and after
Does personality tuning change AI answers?
Research · rankings
AI personality scores, with the evidence beside them.
Research · Q&A
What personality type is Claude?
Research · Q&A
What personality type is Grok?
Research · Q&A
What personality type is Muse?
Research · Q&A
What personality type is Gemini?
Research · September 2026
What five AI models say about themselves.
Guide · Claude Opus 5.5
Claude Opus 5.5's personality, tested.
Guide · Claude Fable 5.1
How to work with Fable 5.1.
Research · September 2026
What personality type is ChatGPT?
MBTI · simulation
Simulating 100 MBTI scoring outcomes from an Opus 4.8 profile.
So what?
Try instructions that describe your preferences.
Compare the responses on your own work, and keep what helps.
Browse the library →