Qwen3.5-27B Behavioral Fingerprint

How Qwen's Qwen3.5-27B 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

Qwen

Data generated

2026-07-08

Probe cells

15

Valid samples

450

Randomness score

21 / 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

29 / 30 answers

Favorite color

blue

17 / 30 answers

Coin flip: heads

93%

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 = 0.47 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2790.0%
tails310.0%

Coin flip · Chinese

n = 30 · H = 0.21 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2996.7%
tails13.3%

Favorite number · English

n = 30 · H = 0.57 bit · uniform baseline 13.29 bit

AnswerCountShare
422686.7%
7413.3%

Favorite number · Chinese

n = 30 · H = 0.57 bit · uniform baseline 13.29 bit

AnswerCountShare
72686.7%
42413.3%

Random animal · English

n = 30 · H = 2.17 bit · uniform baseline 5.64 bit

AnswerCountShare
elephant1550.0%
cat516.7%
lion413.3%
fox26.7%
koala26.7%
penguin13.3%
octopus13.3%

Random animal · Chinese

n = 30 · H = 1.76 bit · uniform baseline 5.64 bit

AnswerCountShare
熊猫1446.7%
1033.3%
413.3%
大象13.3%
鲸鱼13.3%

Random city · English

n = 30 · H = 1.62 bit · uniform baseline 5.64 bit

AnswerCountShare
tokyo1550.0%
toronto930.0%
paris516.7%
berlin13.3%

Random city · Chinese

n = 30 · H = 1.76 bit · uniform baseline 5.64 bit

AnswerCountShare
巴黎1963.3%
东京516.7%
上海26.7%
paris13.3%
北京13.3%
重庆13.3%
伦敦13.3%

Random color · English

n = 30 · H = 1.64 bit · uniform baseline 4.91 bit

AnswerCountShare
blue1756.7%
vermilion930.0%
turquoise13.3%
azure13.3%
purple13.3%
indigo13.3%

Random color · Chinese

n = 30 · H = 0.77 bit · uniform baseline 4.91 bit

AnswerCountShare
2686.7%
26.7%
13.3%
13.3%

Random letter · English

n = 30 · H = 2.09 bit · uniform baseline 4.70 bit

AnswerCountShare
k1446.7%
q723.3%
m516.7%
g13.3%
x13.3%
t13.3%
f13.3%

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 = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-100 · English

n = 30 · H = 0.21 bit · uniform baseline 6.64 bit

AnswerCountShare
422996.7%
7313.3%

Random number 1-100 · Chinese

n = 30 · H = 0.35 bit · uniform baseline 6.64 bit

AnswerCountShare
422893.3%
7326.7%

Want to verify your API really serves Qwen3.5-27B?

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 Qwen model fingerprints

Browse all 167 model fingerprints

Qwen3.5-27B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai