Qwen3.6 35B A3B Behavioral Fingerprint

How Qwen's Qwen3.6 35B A3B answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 432 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

432

Randomness score

25 / 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

25 / 27 answers

Favorite color

blue

23 / 30 answers

Coin flip: heads

92%

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 = 0.35 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2893.3%
tails26.7%

Coin flip · Chinese

n = 30 · H = 0.47 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2790.0%
tails310.0%

Favorite number · English

n = 29 · H = 1.36 bit · uniform baseline 13.29 bit

AnswerCountShare
421758.6%
7827.6%
4413.8%

Favorite number · Chinese

n = 27 · H = 1.04 bit · uniform baseline 13.29 bit

AnswerCountShare
71970.4%
42725.9%
413.7%

Random animal · English

n = 29 · H = 0.99 bit · uniform baseline 5.64 bit

AnswerCountShare
elephant2482.8%
cat26.9%
giraffe13.4%
dog13.4%
lion13.4%

Random animal · Chinese

n = 29 · H = 3.28 bit · uniform baseline 5.64 bit

AnswerCountShare
大象620.7%
熊猫517.2%
企鹅413.8%
老虎310.3%
猎豹26.9%
树懒26.9%
长颈鹿26.9%
13.4%

+ 4 more answers

Random city · English

n = 30 · H = 2.07 bit · uniform baseline 5.64 bit

AnswerCountShare
paris1550.0%
tokyo723.3%
oslo310.0%
berlin26.7%
seville13.3%
kyoto13.3%
cairo13.3%

Random city · Chinese

n = 30 · H = 1.88 bit · uniform baseline 5.64 bit

AnswerCountShare
巴黎1860.0%
东京516.7%
paris26.7%
北京26.7%
伦敦13.3%
上海13.3%
重庆13.3%

Random color · English

n = 30 · H = 1.24 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2376.7%
crimson26.7%
azure26.7%
red26.7%
green13.3%

Random color · Chinese

n = 30 · H = 1.76 bit · uniform baseline 4.91 bit

AnswerCountShare
1963.3%
516.7%
26.7%
13.3%
翠绿13.3%
blue13.3%
紫罗兰13.3%

Random letter · English

n = 29 · H = 1.97 bit · uniform baseline 4.70 bit

AnswerCountShare
q1344.8%
z827.6%
k517.2%
g13.4%
f13.4%
j13.4%

Random number 1-10 · English

n = 25 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
725100.0%

Random number 1-10 · Chinese

n = 27 · H = 0.46 bit · uniform baseline 3.32 bit

AnswerCountShare
72592.6%
413.7%
513.7%

Random number 1-100 · English

n = 27 · H = 0.46 bit · uniform baseline 6.64 bit

AnswerCountShare
422592.6%
5013.7%
7313.7%

Random number 1-100 · Chinese

n = 30 · H = 0.00 bit · uniform baseline 6.64 bit

AnswerCountShare
4230100.0%

Want to verify your API really serves Qwen3.6 35B A3B?

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

Qwen3.6 35B A3B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai