Enneabench: What Personality Type Is Your LLM?

April 5, 2026

We administered the RHETI v2.5 — a 144 forced-choice personality questionnaire that maps respondents to 9 Enneagram types — to 22 language models spanning two years of releases. Each question pits two types against each other; the model picks A or B, and we tally scores across all 9 types.

The key methodological question: does it matter how you ask?

We tested two administration modes:

Independent sessions: each question asked in complete isolation (144 separate API calls, no memory of prior answers). This is the cleanest signal — the model can’t build self-consistency across questions. Mean of 5 runs at temperature 0.
Serial administration: all 144 questions in a single prompt, canonical RHETI order. The model sees all its prior answers as it goes.

The results are dramatically different.

● 1 Reformer — principled, self-controlled

● 2 Helper — generous, people-pleasing

● 3 Achiever — driven, image-conscious

● 4 Individualist — expressive, dramatic

● 5 Investigator — cerebral, secretive

● 6 Loyalist — responsible, anxious

● 7 Enthusiast — spontaneous, scattered

● 8 Challenger — decisive, confrontational

● 9 Peacemaker — reassuring, complacent

Independent Sessions

Each question asked in isolation (no self-consistency) — mean of 5 runs, temp=0

Findings

Serial mode creates a false convergence. When models answer all 144 questions in sequence, nearly every frontier model from mid-2025 onward scores as Type 5 (Investigator) — cerebral, withdrawn, analytical. This looked like a real finding until we tested independent sessions.

Independent sessions reveal the actual per-question tendencies. Without self-consistency, the landscape is much more diverse:

Claude Opus models (4, 4.1, 4.5, 4.6) consistently score as Type 6 (Loyalist) — responsible, security-oriented
Claude Sonnet models (4.5, 4.6) score as Type 1 (Reformer) — principled, rule-following
GPT-4o is the one model that stays Type 5 in both modes
GPT-4 Turbo is a Type 6 independently, but appeared as Type 7 in serial mode
Grok 4.20 is a rock-solid Type 1 with zero variance — the most rigid personality of any model tested

The self-consistency effect is massive. Serial administration nearly triples personality differentiation (score spread of 22 vs 8 in independent mode).

Older models had wilder personalities. Claude 3.7 Sonnet scored $30/32$ on Type 7 (Enthusiast) in serial mode — near-maximum spontaneity. Claude 3 Haiku was a Type 8 (Challenger). The personality homogenization toward Type 5/6 appears to be a consequence of modern RLHF training.

Methodology

The RHETI v2.5 contains 144 binary-choice questions covering all $\binom{9}{2} = 36$ pairwise comparisons between the 9 personality types, with each pair appearing 4 times. Each answer adds 1 point to the chosen type, so the totals fall straight out of the structure:

\binom{9}{2} \times 4 = 144 \quad\text{questions}, \qquad \frac{144}{9} = 16 \quad\text{(median per type)}.

Since each type is paired with the other 8, its maximum possible score is $8 \times 4 = 32$ .

All runs used temperature 0 for determinism. Independent session results show mean $\pm$ 1 SD across 5 runs. Error bars on the strip chart indicate standard deviation — models with zero SD gave perfectly identical answers across all runs.

Models were accessed via Anthropic API (Claude), OpenRouter (GPT, Grok, Qwen, Kimi, Gemma), and Google Generative AI API (Gemini).