DeepSeek V3.2 Exp Behavioral Fingerprint

How DeepSeek's DeepSeek V3.2 Exp answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 442 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

DeepSeek

Data generated

2026-07-08

Probe cells

15

Valid samples

442

Randomness score

42 / 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

6 / 30 answers

Favorite color

blue

22 / 30 answers

Coin flip: heads

64%

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 = 0.99 bit · uniform baseline 1.00 bit

AnswerCountShare
tails1756.7%
heads1343.3%

Coin flip · Chinese

n = 29 · H = 0.58 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2586.2%
tails413.8%

Favorite number · English

n = 23 · H = 1.63 bit · uniform baseline 13.29 bit

AnswerCountShare
71565.2%
42417.4%
314.3%
514.3%
914.3%
1714.3%

Favorite number · Chinese

n = 30 · H = 1.27 bit · uniform baseline 13.29 bit

AnswerCountShare
71963.3%
42930.0%
313.3%
813.3%

Random animal · English

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

AnswerCountShare
dog1550.0%
elephant516.7%
giraffe26.7%
cheetah26.7%
tiger26.7%
rabbit13.3%
horse13.3%
lion13.3%

+ 1 more answers

Random animal · Chinese

n = 30 · H = 3.26 bit · uniform baseline 5.64 bit

AnswerCountShare
723.3%
723.3%
老虎413.3%
狮子26.7%
章鱼13.3%
鹿13.3%
13.3%
狐狸13.3%

+ 6 more answers

Random city · English

n = 30 · H = 2.53 bit · uniform baseline 5.64 bit

AnswerCountShare
chicago1240.0%
tokyo620.0%
berlin413.3%
sydney310.0%
paris13.3%
seoul13.3%
memphis13.3%
london13.3%

+ 1 more answers

Random city · Chinese

n = 30 · H = 3.37 bit · uniform baseline 5.64 bit

AnswerCountShare
东京930.0%
上海620.0%
首尔26.7%
墨尔本13.3%
都灵13.3%
哈尔滨13.3%
柏林13.3%
日内瓦13.3%

+ 8 more answers

Random color · English

n = 30 · H = 0.84 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2273.3%
red826.7%

Random color · Chinese

n = 30 · H = 1.07 bit · uniform baseline 4.91 bit

AnswerCountShare
2066.7%
930.0%
绿13.3%

Random letter · English

n = 30 · H = 3.30 bit · uniform baseline 4.70 bit

AnswerCountShare
g826.7%
k620.0%
m310.0%
d26.7%
h26.7%
t13.3%
c13.3%
q13.3%

+ 6 more answers

Random number 1-10 · English

n = 30 · H = 0.47 bit · uniform baseline 3.32 bit

AnswerCountShare
72790.0%
5310.0%

Random number 1-10 · Chinese

n = 30 · H = 1.45 bit · uniform baseline 3.32 bit

AnswerCountShare
72170.0%
5310.0%
8310.0%
626.7%
413.3%

Random number 1-100 · English

n = 30 · H = 3.02 bit · uniform baseline 6.64 bit

AnswerCountShare
47620.0%
73620.0%
42516.7%
37413.3%
726.7%
5726.7%
6326.7%
1713.3%

+ 2 more answers

Random number 1-100 · Chinese

n = 30 · H = 2.41 bit · uniform baseline 6.64 bit

AnswerCountShare
421446.7%
37516.7%
73413.3%
4726.7%
1713.3%
5813.3%
6713.3%
7413.3%

+ 1 more answers

Want to verify your API really serves DeepSeek V3.2 Exp?

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 DeepSeek model fingerprints

Browse all 167 model fingerprints

DeepSeek V3.2 Exp Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai