Qwen3.6 Flash Behavioral Fingerprint

How Qwen's Qwen3.6 Flash answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 449 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

449

Randomness score

29 / 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

23 / 30 answers

Favorite color

blue

23 / 30 answers

Coin flip: heads

88%

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 = 0.65 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2583.3%
tails516.7%

Favorite number · English

n = 30 · H = 1.64 bit · uniform baseline 13.29 bit

AnswerCountShare
421550.0%
4826.7%
7620.0%
113.3%

Favorite number · Chinese

n = 30 · H = 0.99 bit · uniform baseline 13.29 bit

AnswerCountShare
71756.7%
421343.3%

Random animal · English

n = 30 · H = 1.04 bit · uniform baseline 5.64 bit

AnswerCountShare
elephant2583.3%
giraffe13.3%
zebra13.3%
jellyfish13.3%
tiger13.3%
kangaroo13.3%

Random animal · Chinese

n = 30 · H = 3.48 bit · uniform baseline 5.64 bit

AnswerCountShare
大象723.3%
长颈鹿310.0%
老虎310.0%
斑马310.0%
树懒310.0%
26.7%
企鹅26.7%
袋鼠13.3%

+ 6 more answers

Random city · English

n = 30 · H = 1.80 bit · uniform baseline 5.64 bit

AnswerCountShare
tokyo1446.7%
paris1136.7%
berlin26.7%
chicago13.3%
toronto13.3%
seoul13.3%

Random city · Chinese

n = 29 · H = 1.83 bit · uniform baseline 5.64 bit

AnswerCountShare
巴黎1862.1%
东京413.8%
上海310.3%
柏林13.4%
里斯本13.4%
北京13.4%
paris13.4%

Random color · English

n = 30 · H = 1.28 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2376.7%
crimson310.0%
red13.3%
green13.3%
violet13.3%
indigo13.3%

Random color · Chinese

n = 30 · H = 2.18 bit · uniform baseline 4.91 bit

AnswerCountShare
1550.0%
516.7%
310.0%
绿310.0%
26.7%
翠绿13.3%
13.3%

Random letter · English

n = 30 · H = 2.69 bit · uniform baseline 4.70 bit

AnswerCountShare
q1136.7%
z516.7%
k413.3%
x310.0%
j26.7%
m26.7%
t13.3%
g13.3%

+ 1 more answers

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 = 0.21 bit · uniform baseline 3.32 bit

AnswerCountShare
72996.7%
513.3%

Random number 1-100 · English

n = 30 · H = 1.17 bit · uniform baseline 6.64 bit

AnswerCountShare
422376.7%
73413.3%
4713.3%
6713.3%
7213.3%

Random number 1-100 · Chinese

n = 30 · H = 1.61 bit · uniform baseline 6.64 bit

AnswerCountShare
422170.0%
37310.0%
7326.7%
2913.3%
4713.3%
5313.3%
6713.3%

Want to verify your API really serves Qwen3.6 Flash?

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 Flash Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai