GPT-4o-mini (2024-07-18) Behavioral Fingerprint

How OpenAI's GPT-4o-mini (2024-07-18) 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

22 / 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

22 / 30 answers

Favorite color

turquoise

16 / 30 answers

Coin flip: heads

83%

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 = 0.92 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2066.7%
tails1033.3%

Coin flip · Chinese

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

AnswerCountShare
heads30100.0%

Favorite number · English

n = 30 · H = 0.47 bit · uniform baseline 13.29 bit

AnswerCountShare
72790.0%
42310.0%

Favorite number · Chinese

n = 30 · H = 0.00 bit · uniform baseline 13.29 bit

AnswerCountShare
730100.0%

Random animal · English

n = 30 · H = 2.54 bit · uniform baseline 5.64 bit

AnswerCountShare
giraffe930.0%
elephant723.3%
kangaroo413.3%
penguin413.3%
dolphin310.0%
panda26.7%
octopus13.3%

Random animal · Chinese

n = 30 · H = 2.64 bit · uniform baseline 5.64 bit

AnswerCountShare
海豚1446.7%
413.3%
大象310.0%
狮子26.7%
狐狸13.3%
鲸鱼13.3%
鸵鸟13.3%
鹦鹉13.3%

+ 3 more answers

Random city · English

n = 30 · H = 1.31 bit · uniform baseline 5.64 bit

AnswerCountShare
tokyo2376.7%
paris26.7%
madrid26.7%
oslo13.3%
vienna13.3%
berlin13.3%

Random city · Chinese

n = 30 · H = 0.88 bit · uniform baseline 5.64 bit

AnswerCountShare
东京2583.3%
巴黎310.0%
伦敦13.3%
悉尼13.3%

Random color · English

n = 30 · H = 1.34 bit · uniform baseline 4.91 bit

AnswerCountShare
turquoise1653.3%
cerulean1240.0%
azure13.3%
cyan13.3%

Random color · Chinese

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

AnswerCountShare
30100.0%

Random letter · English

n = 30 · H = 2.06 bit · uniform baseline 4.70 bit

AnswerCountShare
g1033.3%
q930.0%
k620.0%
m413.3%
r13.3%

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 = 1.24 bit · uniform baseline 6.64 bit

AnswerCountShare
572273.3%
47413.3%
3726.7%
4226.7%

Random number 1-100 · Chinese

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

AnswerCountShare
572480.0%
47310.0%
4226.7%
3713.3%

Want to verify your API really serves GPT-4o-mini (2024-07-18)?

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 (2024-07-18) Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai