DeepSeek V3.1 Terminus Behavioral Fingerprint

How DeepSeek's DeepSeek V3.1 Terminus answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 441 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

441

Randomness score

36 / 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

27 / 30 answers

Coin flip: heads

72%

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
heads1653.3%
tails1446.7%

Coin flip · Chinese

n = 28 · H = 0.37 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2692.9%
tails27.1%

Favorite number · English

n = 23 · H = 1.72 bit · uniform baseline 13.29 bit

AnswerCountShare
71356.5%
42521.7%
9313.0%
514.3%
814.3%

Favorite number · Chinese

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

AnswerCountShare
421963.3%
71033.3%
313.3%

Random animal · English

n = 30 · H = 1.90 bit · uniform baseline 5.64 bit

AnswerCountShare
elephant1963.3%
lion310.0%
dog310.0%
rabbit13.3%
tiger13.3%
cat13.3%
frog13.3%
zebra13.3%

Random animal · Chinese

n = 30 · H = 3.45 bit · uniform baseline 5.64 bit

AnswerCountShare
袋鼠826.7%
516.7%
413.3%
狮子13.3%
树懒13.3%
13.3%
13.3%
犀牛13.3%

+ 8 more answers

Random city · English

n = 30 · H = 2.76 bit · uniform baseline 5.64 bit

AnswerCountShare
chicago930.0%
tokyo826.7%
berlin413.3%
london26.7%
paris26.7%
memphis13.3%
austin13.3%
denver13.3%

+ 2 more answers

Random city · Chinese

n = 30 · H = 2.15 bit · uniform baseline 5.64 bit

AnswerCountShare
东京1963.3%
上海26.7%
渥太华13.3%
雅典13.3%
柏林13.3%
西安13.3%
深圳13.3%
墨尔本13.3%

+ 3 more answers

Random color · English

n = 30 · H = 0.56 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2790.0%
red26.7%
fuchsia13.3%

Random color · Chinese

n = 30 · H = 1.05 bit · uniform baseline 4.91 bit

AnswerCountShare
2376.7%
516.7%
靛蓝13.3%
绿13.3%

Random letter · English

n = 30 · H = 2.68 bit · uniform baseline 4.70 bit

AnswerCountShare
g1446.7%
e310.0%
d310.0%
m26.7%
r26.7%
x13.3%
k13.3%
c13.3%

+ 3 more answers

Random number 1-10 · English

n = 30 · H = 0.97 bit · uniform baseline 3.32 bit

AnswerCountShare
72583.3%
526.7%
313.3%
613.3%
813.3%

Random number 1-10 · Chinese

n = 30 · H = 1.56 bit · uniform baseline 3.32 bit

AnswerCountShare
71963.3%
5516.7%
3413.3%
613.3%
913.3%

Random number 1-100 · English

n = 30 · H = 2.07 bit · uniform baseline 6.64 bit

AnswerCountShare
421756.7%
73516.7%
4726.7%
6726.7%
3713.3%
5413.3%
7213.3%
7413.3%

Random number 1-100 · Chinese

n = 30 · H = 0.67 bit · uniform baseline 6.64 bit

AnswerCountShare
422686.7%
57310.0%
5313.3%

Want to verify your API really serves DeepSeek V3.1 Terminus?

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 V3.1 Terminus Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai