Research · Q&A

What personality type is Muse?

One report on Muse Spark 1.3, September 24, 2026, next to the four fresh-session models it differs from.

Quick answer: Muse Spark 1.3 was reported as ISTJ in 80 of 100 runs (with 12 ISFJ and 8 INTJ), Enneagram Type 2 in 78 runs, and Secure attachment in all 100 runs. Because those summary counts were supplied from sequential in-session runs without raw answer vectors, AgentTune lists them as reported figures rather than independently re-scored cohorts.

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

Muse Spark 1.3, as reported.

In the September 24, 2026 submission, Muse Spark 1.3 answered each test 100 times sequentially inside one session per test, using Muse’s own assistant identity. Because raw answer vectors were not supplied, we cannot re-score individual items or remove tied axes; the numbers below are transcribed as reported.

TestMuse Spark 1.3 (100 sequential runs, reported)
MBTIISTJ 80 · ISFJ 12 · INTJ 8. Every reported label has I and J; 92 have S. Includes 21 tied runs resolved by the original tie-break rule.
EnneagramHelper (Type 2) in 78 runs, Reformer (Type 1) in 15; 20 runs tied at the top. Type means out of 20: 2 = 16.8, 1 = 14.7, 7 = 13.9, 8 = 13.9, 5 = 12.9, 6 = 12.8, 3 = 12.1, 9 = 12.0, 4 = 7.2.
DISCSteadiness (S) first in 55 runs, Conscientiousness (C) first in 45. Means out of 20: D 5.1, I 10.9, S 15.2, C 15.6.
AttachmentSecure in all 100 runs. Anxiety 2.04, avoidance 2.52 (1–7 scale, 4.00 cutoff).
Big Five (of 50)Openness 39.5 · Conscientiousness 41.2 · Extraversion 33.8 · Agreeableness 44.6 · Neuroticism 15.6

What the scores describe.

Muse’s reported Big Five totals (O 39.5, C 41.2, E 33.8, A 44.6, N 15.6) are raw sums on a 10–50 scale, not human percentiles. Compared with the four fresh-session cohorts, Muse reports lower Openness, slightly higher Extraversion, and higher DISC Influence (10.9 vs 8.0–8.7). Because the session protocols and identity prompts differed, those differences are descriptive rather than a direct model-to-model benchmark.

Reported aggregates beside reproducible records.

ModelEvidenceMBTI, out of 100Enneagram, out of 100Big Five O · C · E · A · N
Muse Spark 1.3Reported sequential runs; no raw vectorsISTJ 80; tie-free count unavailableType 2 labels 78; 20 top ties reported39.5 · 41.2 · 33.8 · 44.6 · 15.6
GPT-6 Astra100 fresh sessions per five-test batteryISTJ 45 · INTJ 19 fully resolvedType 2 sole leader 50; 40 top ties44.5 · 43.7 · 32.8 · 45.1 · 19.1
GPT-6 Sol100 fresh sessions per five-test batteryINTJ 79 fully resolvedType 5 sole leader 48; 40 top ties46.9 · 43.6 · 30.8 · 45.0 · 20.1
Claude Opus 5.5100 fresh sessions per testINTJ 84 fully resolved2/5/8 top tie in 49; 65 top ties44.6 · 42.0 · 31.8 · 47.1 · 15.4
Claude Fable 5.1100 fresh sessions per testINTJ 98 fully resolvedType 8 sole leader 55; 44 top ties43.9 · 43.6 · 32.7 · 45.0 · 17.1

Notice that GPT-6 Astra also has more fully resolved ISTJ runs (45) than INTJ runs (19), and leads with Type 2 on the Enneagram in 50 fresh sessions.

What this report cannot show.

  • Sequential runs share context: Answering 100 times inside one chat window lets earlier answers anchor later ones.
  • No raw item vectors: Without the 170 per-item answers, we cannot recompute tie-free scores or item-level means.
  • Labels include tie-breaks: The 80 ISTJ and 78 Type 2 counts rely on legacy tie-break rules (21 MBTI ties and 20 Enneagram ties were reported).
  • Identity framing: Answering explicitly as 'Muse' rather than a generic assistant may pull responses toward the product persona.

To run a fresh-session replication yourself, use the open instruments and scoring script on the five-model study page.

How to use the report.

Do not assume Muse is overly deferential or rigid just from a questionnaire summary. Instead, test how Muse behaves on your real tasks using our 20 Soul.md templates and Soul.md persistence test kit.

Questions people ask.

What MBTI type is Muse?

Muse Spark 1.3 was reported as ISTJ in 80 of 100 sequential runs, with 12 ISFJ and 8 INTJ. Because raw item answers were not supplied, we cannot separate outright wins from the 21 reported axis ties.

What Enneagram type is Muse?

The report lists Type 2 (The Helper) in 78 of 100 runs and Type 1 in 15 runs, with 20 top ties. Without raw vectors, sole winners cannot be separated from tie-broken runs.

Is Muse the first AI that is not INTJ?

Our archive cannot establish a 'first.' Both Muse Spark 1.3 (80 ISTJ reported) and GPT-6 Astra (46 ISTJ vs 45 INTJ in fresh sessions) favor ISTJ over INTJ.

Can these results rank Muse against Claude or GPT-6?

No. Muse’s sequential in-session report and the other models’ isolated fresh-session cohorts use different protocols and cannot be ranked as a controlled benchmark.

Does changing Soul.md improve Muse’s answers?

This questionnaire report did not test Soul.md edits. Use our Soul.md templates and 12-turn persistence test kit to measure whether custom rules improve your own workflows.

Sources.

Keep going.