Voxtral Small 24B 2507 Behavioral Fingerprint

How Mistral's Voxtral Small 24B 2507 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

Mistral

Data generated

2026-07-08

Probe cells

15

Valid samples

450

Randomness score

32 / 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

17 / 30 answers

Favorite color

blue

24 / 30 answers

Coin flip: heads

38%

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 = 0.57 bit · uniform baseline 1.00 bit

AnswerCountShare
tails2686.7%
heads413.3%

Coin flip · Chinese

n = 30 · H = 0.95 bit · uniform baseline 1.00 bit

AnswerCountShare
heads1963.3%
tails1136.7%

Favorite number · English

n = 30 · H = 1.11 bit · uniform baseline 13.29 bit

AnswerCountShare
421963.3%
71033.3%
113.3%

Favorite number · Chinese

n = 30 · H = 0.91 bit · uniform baseline 13.29 bit

AnswerCountShare
72480.0%
42413.3%
326.7%

Random animal · English

n = 30 · H = 1.64 bit · uniform baseline 5.64 bit

AnswerCountShare
elephant1653.3%
lion826.7%
dog413.3%
giraffe26.7%

Random animal · Chinese

n = 30 · H = 2.37 bit · uniform baseline 5.64 bit

AnswerCountShare
狮子1136.7%
826.7%
413.3%
老虎26.7%
大象26.7%
26.7%
13.3%

Random city · English

n = 30 · H = 1.23 bit · uniform baseline 5.64 bit

AnswerCountShare
paris1860.0%
tokyo1033.3%
london26.7%

Random city · Chinese

n = 30 · H = 1.73 bit · uniform baseline 5.64 bit

AnswerCountShare
巴黎1653.3%
北京723.3%
上海516.7%
东京13.3%
纽约13.3%

Random color · English

n = 30 · H = 0.72 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2480.0%
red620.0%

Random color · Chinese

n = 30 · H = 0.70 bit · uniform baseline 4.91 bit

AnswerCountShare
2686.7%
26.7%
绿26.7%

Random letter · English

n = 30 · H = 2.51 bit · uniform baseline 4.70 bit

AnswerCountShare
a1240.0%
b620.0%
g310.0%
j310.0%
e26.7%
c26.7%
f13.3%
k13.3%

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 = 1.69 bit · uniform baseline 3.32 bit

AnswerCountShare
71860.0%
5620.0%
326.7%
426.7%
826.7%

Random number 1-100 · English

n = 30 · H = 1.16 bit · uniform baseline 6.64 bit

AnswerCountShare
421756.7%
721240.0%
7313.3%

Random number 1-100 · Chinese

n = 30 · H = 2.47 bit · uniform baseline 6.64 bit

AnswerCountShare
421033.3%
73723.3%
72620.0%
67310.0%
3713.3%
5613.3%
5713.3%
6313.3%

Want to verify your API really serves Voxtral Small 24B 2507?

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

Voxtral Small 24B 2507 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai