Source: https://agent-tune.com/guides/open-personality-tests
Format: page-specific Markdown. Tables preserve row order; interactive controls are available on the source page.

Guide · Tests

# Questionnaires, scores and their limits.

        By Bernard Huang · Updated September 26, 2026

        All five tests run locally in your browser with instant results and no signup. The four restored tests preserve their previous website editions; Big Five reports raw totals and means. A questionnaire score is not a diagnosis or evidence that a tuning improves performance.

## Current availability

        Take the [MBTI-style](https://agent-tune.com/tests/mbti), [Enneagram](https://agent-tune.com/tests/enneagram), [DISC](https://agent-tune.com/tests/disc), [attachment](https://agent-tune.com/tests/attachment) or [Big Five](https://agent-tune.com/tests/big-five) questionnaire. Complete all items to view a score; tied results stay explicit.

Read the [per-instrument rights record](https://agent-tune.com/resources/content/instrument-rights.json) before reusing questionnaire material. Original software and template licenses do not relicense third-party question text.

## Big Five scoring

        Complete all 50 items using the versioned response scale. Reverse keyed items use 6 minus the response. Each dimension sums ten scored items (10–50); its average is the total divided by ten (1–5). Invalid values are rejected and missing responses produce no final score.

Current results contain no population percentiles, reference indices or automatic template selection. Neuroticism reverses the direction of IPIP Emotional Stability; Openness corresponds to Intellect/Imagination. The [specification](https://agent-tune.com/tests/big-five.md) records the adaptation.

## Historical research scoring

        Published studies used legacy adaptations and, in some cases, deterministic tie-break labels. MBTI item 1 and two Enneagram items had undocumented substitutions. Preserve those edition identities when interpreting the results. Raw vectors and numerical results remain unchanged; restricted item wording in public downloads is replaced by stable item labels.

[Correction and source hashes](https://agent-tune.com/research/data/rights-migration.json) · [Reproduce the arithmetic](https://agent-tune.com/guides/reproduce-ai-personality-research).

## Choose behavior explicitly

        Questionnaires are optional. Use the [preference builder](https://agent-tune.com/tools/custom-instructions-generator) to request the detail, warmth, structure and pushback you want. Review each rule before saving it. No framework or score outranks your explicit request, accuracy or authorized scope.

## Questions people ask.

            Are all five questionnaires MIT licensed?

            No. Original AgentTune templates and code have their own license; instrument content has separate terms. Review the rights record before reuse.

            Does the Big Five result show a population percentile?

            No. It reports raw dimension totals and item means. The former reference constants had no verified normative sample.

## What changed.

- September 25, 2026 First published.

## Sources.

- [AgentTune tests hub (items, scales and scoring rules for all five)](https://agent-tune.com/tests/)

- [Open Psychometrics Project: OEJTS](https://openpsychometrics.org/tests/OEJTS/)

- [IPIP: the 50-item Big Five markers](https://ipip.ori.org/)

- [Fraley, Waller and Brennan (2000), the ECR-R](https://doi.org/10.1037/0022-3514.78.2.350)

- [What five AI models say about themselves (how the tests were run on models)](https://agent-tune.com/research/ai-personality-five-models-2026)

## Keep going.

          [TestsTake any of the five](https://agent-tune.com/tests/)
          [GuideOpen-source Enneagram test and scorer](https://agent-tune.com/guides/open-source-enneagram-test)
          [GuideMBTI vs Big Five for AI](https://agent-tune.com/guides/mbti-vs-big-five-for-ai)
          [ResearchThe research hub](https://agent-tune.com/research)