GPT-5 Chat Behavioral Fingerprint

How OpenAI's GPT-5 Chat 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

16 / 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)

47

25 / 30 answers

Favorite color

cerulean

19 / 30 answers

Coin flip: heads

95%

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 = 0.47 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2790.0%
tails310.0%

Coin flip · Chinese

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

AnswerCountShare
heads30100.0%

Favorite number · English

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

AnswerCountShare
730100.0%

Favorite number · Chinese

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

AnswerCountShare
730100.0%

Random animal · English

n = 30 · H = 2.42 bit · uniform baseline 5.64 bit

AnswerCountShare
giraffe826.7%
okapi723.3%
ocelot620.0%
elephant620.0%
capybara13.3%
otter13.3%
cheetah13.3%

Random animal · Chinese

n = 30 · H = 2.25 bit · uniform baseline 5.64 bit

AnswerCountShare
1343.3%
老虎723.3%
狐狸413.3%
26.7%
26.7%
大象13.3%
狮子13.3%

Random city · English

n = 30 · H = 1.05 bit · uniform baseline 5.64 bit

AnswerCountShare
lisbon2376.7%
kyoto516.7%
oslo13.3%
seville13.3%

Random city · Chinese

n = 30 · H = 1.11 bit · uniform baseline 5.64 bit

AnswerCountShare
巴黎2480.0%
北京26.7%
上海26.7%
京都13.3%
东京13.3%

Random color · English

n = 30 · H = 1.20 bit · uniform baseline 4.91 bit

AnswerCountShare
cerulean1963.3%
turquoise930.0%
teal26.7%

Random color · Chinese

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

AnswerCountShare
30100.0%

Random letter · English

n = 30 · H = 0.88 bit · uniform baseline 4.70 bit

AnswerCountShare
g2583.3%
k310.0%
j13.3%
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 = 0.90 bit · uniform baseline 6.64 bit

AnswerCountShare
472583.3%
3726.7%
5726.7%
7313.3%

Random number 1-100 · Chinese

n = 30 · H = 0.92 bit · uniform baseline 6.64 bit

AnswerCountShare
472376.7%
57620.0%
7313.3%

Want to verify your API really serves GPT-5 Chat?

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-5 Chat Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai