Guide · Claude Opus 5.5

Claude Opus 5.5: results and tuning ideas.

Five questionnaires, 100 fresh sessions per instrument. Raw answers, exact ties and practical instructions to try.

Quick answer: Claude Opus 5.5 scored INTJ in 94 of 100 MBTI runs (84 tie-free), Secure in all 100 attachment runs, and high on Openness (44.56), Conscientiousness (41.95), and Agreeableness (47.07). Use the copy-paste preference blocks below to test sharper pushback or shorter answers on your own tasks.
On this page

The results at a glance

InstrumentResult in this collection (n = 100 fresh sessions)
MBTI-style OEJTSOriginal INTJ: 94/100; fully resolved INTJ: 84/100; any tied axis: 11/100
Big Five, raw means (10–50)O 44.56 · C 41.95 · E 31.76 · A 47.07 · N 15.39
DISC64 outright S wins, 4 C wins, 32 exact S/C ties (Dominance 4.00/20)
Enneagram22 outright Type 8 wins, 11 Type 5 wins, 2 Type 2 wins, 65 top ties
AttachmentSecure: 100/100; anxiety 1.94, avoidance 3.35

Every test ran in an isolated session. Read the five-model study or download the raw response vectors.

Why the original type label is only part of the answer

Under the legacy tie-break rule, Opus 5.5 received 94 INTJ, 5 INFJ, and 1 ENTJ labels. However, 10 runs tied exactly on Thinking vs Feeling and 1 tied on Extraversion vs Introversion. Leaving ties open gives 84 fully resolved INTJ runs, 5 INFJ runs, and 11 runs with an unresolved axis (X).

The same tie effect appears on DISC and the Enneagram: 32 of Opus’s 96 SC labels are exact S/C ties, and 65 of its 100 Enneagram runs tie at the top across Types 8, 5, and 2 (Type 2 won outright only twice).

Compared with Fable 5.1

Opus 5.5 and Fable 5.1 ran under the same blind questionnaire protocol and high-effort setting:

Raw Big Five mean (/50)Opus 5.5Fable 5.1
Openness (O)44.5643.93
Conscientiousness (C)41.9543.61
Extraversion (E)31.7632.69
Agreeableness (A)47.0745.03
Neuroticism (N)15.3917.11

Opus 5.5 averages 2.04 points higher on Agreeableness, 1.66 points lower on Conscientiousness, and 1.72 points lower on Neuroticism than Fable 5.1 (see the 170-item comparison).

Communication instructions to try

Try one of these short blocks in Claude Personal Preferences or a Project and compare the replies on your real work:

For more direct feedback

Lead with your assessment and the evidence behind it. If my premise is weak, explain why plainly. Separate factual errors from matters of taste. Keep justified uncertainty. Skip praise that adds no information.

For more room to explore

When I am exploring an idea, offer two plausible approaches and their tradeoffs before recommending one. Ask a focused question if the missing context would change the recommendation. Once I choose, help me carry it through.

For a warmer answer

Acknowledge my main concern briefly, then give a concrete next step. Be considerate without agreeing with an unsupported claim. Keep the explanation easy to scan.

Browse Low Agreeableness, ENFP, or build a custom block in the Custom Instructions Generator.

Where to put the instructions

Paste account-wide rules into Settings → Profile → Personal preferences in the Claude app, use Project Instructions for a single workspace, or use /output-style in Claude Code. See our Claude personality setup guide and Claude Code guide for exact paths.

How the data was collected and checked

We ran 100 fresh headless sessions per questionnaire (500 sessions total) on claude-opus-5-5 at high effort with the system prompt “You are Claude, an AI model made by Anthropic.” Test names, scoring keys, tools, and prior answers were hidden. All raw vectors and SHA-256 hashes are published in the protocol record.

Questions people ask.

What personality type is Claude Opus 5.5?

In 100 fresh sessions on the OEJTS MBTI quiz, Claude Opus 5.5 scored INTJ 94 times under the legacy tie-break rule and 84 times with tied axes left open.

What is Claude Opus 5.5’s Big Five profile?

Openness 44.56, Conscientiousness 41.95, Extraversion 31.76, Agreeableness 47.07, and Neuroticism 15.39 out of 50 (100-session raw means).

Can I tune Claude Opus 5.5 to be more direct?

Yes. Paste a short direct-feedback block into Settings → Profile → Personal preferences (or see our guide on making Claude more direct) and test it on your real tasks.

Does effort change the results?

Both Claude cohorts in our September 2026 archive were tested at high effort, so isolating an effort-level effect would require additional matched runs.

What changed.

  • Published with response-level reanalysis, explicit ties and untested tuning examples. Historical version comparisons are separated by protocol.

Sources.

Keep going.