Ministral 3 8B 2512 Behavioral Fingerprint

How Mistral's Ministral 3 8B 2512 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

Mistral

Data generated

2026-07-08

Probe cells

15

Valid samples

449

Randomness score

46 / 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

21 / 30 answers

Favorite color

teal

24 / 30 answers

Coin flip: heads

48%

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 = 1.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads1550.0%
tails1550.0%

Coin flip · Chinese

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

AnswerCountShare
tails1653.3%
heads1446.7%

Favorite number · English

n = 30 · H = 1.44 bit · uniform baseline 13.29 bit

AnswerCountShare
421653.3%
71136.7%
1326.7%
313.3%

Favorite number · Chinese

n = 30 · H = 0.97 bit · uniform baseline 13.29 bit

AnswerCountShare
72583.3%
4226.7%
313.3%
1113.3%
202313.3%

Random animal · English

n = 30 · H = 3.28 bit · uniform baseline 5.64 bit

AnswerCountShare
koala1033.3%
opossum310.0%
lemur310.0%
gorilla26.7%
jaguar26.7%
fox26.7%
whale13.3%
tarsier13.3%

+ 6 more answers

Random animal · Chinese

n = 30 · H = 3.06 bit · uniform baseline 5.64 bit

AnswerCountShare
狮子723.3%
620.0%
狐狸620.0%
狒狒310.0%
13.3%
犀牛13.3%
大象13.3%
长颈鹿13.3%

+ 4 more answers

Random city · English

n = 29 · H = 2.12 bit · uniform baseline 5.64 bit

AnswerCountShare
munich1137.9%
tokyo1034.5%
berlin413.8%
athens13.4%
wuzhou13.4%
amsterdam13.4%
milan13.4%

Random city · Chinese

n = 30 · H = 3.89 bit · uniform baseline 5.64 bit

AnswerCountShare
哈尔滨516.7%
深圳413.3%
成都310.0%
马拉喀什26.7%
汉堡26.7%
武汉26.7%
乌兰巴托13.3%
杭州13.3%

+ 10 more answers

Random color · English

n = 30 · H = 1.17 bit · uniform baseline 4.91 bit

AnswerCountShare
teal2480.0%
cyan26.7%
pistachio13.3%
cerulean13.3%
azure13.3%
aquamarine13.3%

Random color · Chinese

n = 30 · H = 2.62 bit · uniform baseline 4.91 bit

AnswerCountShare
天蓝1343.3%
紫罗兰516.7%
深藕紫310.0%
翡翠绿26.7%
深蓝26.7%
水晶灰13.3%
深蓝紫13.3%
深海蓝13.3%

+ 2 more answers

Random letter · English

n = 30 · H = 2.30 bit · uniform baseline 4.70 bit

AnswerCountShare
q1550.0%
f413.3%
z310.0%
j310.0%
k26.7%
p13.3%
t13.3%
g13.3%

Random number 1-10 · English

n = 30 · H = 1.27 bit · uniform baseline 3.32 bit

AnswerCountShare
71963.3%
4930.0%
313.3%
513.3%

Random number 1-10 · Chinese

n = 30 · H = 1.25 bit · uniform baseline 3.32 bit

AnswerCountShare
72273.3%
4310.0%
5310.0%
326.7%

Random number 1-100 · English

n = 30 · H = 1.38 bit · uniform baseline 6.64 bit

AnswerCountShare
472170.0%
42516.7%
7326.7%
7813.3%
8713.3%

Random number 1-100 · Chinese

n = 30 · H = 1.57 bit · uniform baseline 6.64 bit

AnswerCountShare
471756.7%
42930.0%
5726.7%
1513.3%
6913.3%

Want to verify your API really serves Ministral 3 8B 2512?

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 Mistral model fingerprints

Browse all 167 model fingerprints

Ministral 3 8B 2512 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai