Gemini 2.5 Flash Behavioral Fingerprint

How Google's Gemini 2.5 Flash answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 449 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Google

Data generated

2026-07-08

Probe cells

15

Valid samples

449

Randomness score

38 / 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)

42

14 / 30 answers

Favorite color

red

13 / 30 answers

Coin flip: heads

60%

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 = 1.00 bit · uniform baseline 1.00 bit

AnswerCountShare
tails1550.0%
heads1550.0%

Favorite number · English

n = 30 · H = 0.42 bit · uniform baseline 13.29 bit

AnswerCountShare
422893.3%
613.3%
172913.3%

Favorite number · Chinese

n = 29 · H = 1.95 bit · uniform baseline 13.29 bit

AnswerCountShare
71758.6%
42413.8%
8310.3%
326.9%
913.4%
1013.4%
2413.4%

Random animal · English

n = 30 · H = 2.96 bit · uniform baseline 5.64 bit

AnswerCountShare
tiger723.3%
dog620.0%
lion516.7%
cat516.7%
camel13.3%
penguin13.3%
giraffe13.3%
elephant13.3%

+ 3 more answers

Random animal · Chinese

n = 30 · H = 2.28 bit · uniform baseline 5.64 bit

AnswerCountShare
1343.3%
826.7%
老虎310.0%
狮子26.7%
海鸥13.3%
13.3%
13.3%
蜂鸟13.3%

Random city · English

n = 30 · H = 1.89 bit · uniform baseline 5.64 bit

AnswerCountShare
london1550.0%
paris826.7%
tokyo413.3%
lisbon13.3%
cairo13.3%
beijing13.3%

Random city · Chinese

n = 30 · H = 2.40 bit · uniform baseline 5.64 bit

AnswerCountShare
巴黎826.7%
上海620.0%
伦敦620.0%
东京620.0%
北京310.0%
开罗13.3%

Random color · English

n = 30 · H = 1.80 bit · uniform baseline 4.91 bit

AnswerCountShare
red1343.3%
blue1240.0%
green26.7%
chartreuse13.3%
purple13.3%
yellow13.3%

Random color · Chinese

n = 30 · H = 1.78 bit · uniform baseline 4.91 bit

AnswerCountShare
1756.7%
620.0%
绿310.0%
26.7%
26.7%

Random letter · English

n = 30 · H = 3.38 bit · uniform baseline 4.70 bit

AnswerCountShare
r620.0%
x413.3%
q310.0%
g310.0%
z310.0%
l26.7%
m26.7%
p26.7%

+ 4 more answers

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 = 1.63 bit · uniform baseline 6.64 bit

AnswerCountShare
421446.7%
731240.0%
5726.7%
6713.3%
8713.3%

Random number 1-100 · Chinese

n = 30 · H = 1.73 bit · uniform baseline 6.64 bit

AnswerCountShare
422066.7%
73310.0%
7226.7%
8226.7%
1513.3%
6713.3%
7613.3%

Want to verify your API really serves Gemini 2.5 Flash?

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 Google model fingerprints

Browse all 167 model fingerprints

Gemini 2.5 Flash Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai