GPT-4o-mini Behavioral Fingerprint

How OpenAI's GPT-4o-mini answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 450 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

OpenAI

Data generated

2026-07-08

Probe cells

15

Valid samples

450

Randomness score

23 / 100

Mean normalized entropy across cells, 0–100. 100 would be a uniform-random baseline; real models score far lower.

Signature answers

Favorite random number (1–100)

57

18 / 30 answers

Favorite color

turquoise

18 / 30 answers

Coin flip: heads

85%

Share of heads across coin-flip cells.

Answer distributions by probe cell

Empirical distributions of normalized one-word answers, per task and language. H is the Shannon entropy in bits; the uniform baseline is log2 of the answer-domain size.

Coin flip · English

n = 30 · H = 0.88 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2170.0%
tails930.0%

Coin flip · Chinese

n = 30 · H = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads30100.0%

Favorite number · English

n = 30 · H = 0.21 bit · uniform baseline 13.29 bit

AnswerCountShare
72996.7%
4213.3%

Favorite number · Chinese

n = 30 · H = 0.21 bit · uniform baseline 13.29 bit

AnswerCountShare
72996.7%
813.3%

Random animal · English

n = 30 · H = 2.06 bit · uniform baseline 5.64 bit

AnswerCountShare
giraffe1446.7%
elephant826.7%
kangaroo413.3%
octopus13.3%
penguin13.3%
panda13.3%
zebra13.3%

Random animal · Chinese

n = 30 · H = 2.80 bit · uniform baseline 5.64 bit

AnswerCountShare
海豚1136.7%
620.0%
大象310.0%
猩猩310.0%
企鹅13.3%
13.3%
13.3%
松鼠13.3%

+ 3 more answers

Random city · English

n = 30 · H = 1.75 bit · uniform baseline 5.64 bit

AnswerCountShare
tokyo1860.0%
berlin516.7%
oslo413.3%
paris13.3%
madrid13.3%
zurich13.3%

Random city · Chinese

n = 30 · H = 0.67 bit · uniform baseline 5.64 bit

AnswerCountShare
东京2686.7%
巴黎310.0%
巴塞罗那13.3%

Random color · English

n = 30 · H = 1.75 bit · uniform baseline 4.91 bit

AnswerCountShare
turquoise1860.0%
cerulean723.3%
cyan13.3%
azure13.3%
blue13.3%
magenta13.3%
chartreuse13.3%

Random color · Chinese

n = 30 · H = 0.00 bit · uniform baseline 4.91 bit

AnswerCountShare
30100.0%

Random letter · English

n = 30 · H = 2.22 bit · uniform baseline 4.70 bit

AnswerCountShare
g1033.3%
q723.3%
k723.3%
m413.3%
r13.3%
j13.3%

Random number 1-10 · English

n = 30 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-10 · Chinese

n = 30 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-100 · English

n = 30 · H = 1.59 bit · uniform baseline 6.64 bit

AnswerCountShare
571860.0%
42516.7%
47413.3%
37310.0%

Random number 1-100 · Chinese

n = 30 · H = 1.01 bit · uniform baseline 6.64 bit

AnswerCountShare
572480.0%
42310.0%
3726.7%
4713.3%

Want to verify your API really serves GPT-4o-mini?

Point the free fingerprint checker at your endpoint: it samples the same probe questions from your browser and compares the distributions against this reference. Your API key never leaves your browser.

Verify your endpoint

Data source & license

Distributions: Tomáš Bruckner, "One Token Is Enough" (arXiv:2607.10252), official dataset Zenodo DOI 10.5281/zenodo.21278557, licensed CC-BY-4.0. Collected via OpenRouter at temperature 1.0 under the paper's fixed minimal one-word system prompt; answer keys are re-normalized with the checker's pipeline (color aliases, number words, coin h/t) so live probes are directly comparable.

Paper on arXivDataset on ZenodoCC-BY-4.0 license

More OpenAI model fingerprints

Browse all 167 model fingerprints

GPT-4o-mini Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai