Qwen3 235B A22B Behavioral Fingerprint

How Qwen's Qwen3 235B A22B 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

26 / 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

27 / 30 answers

Favorite color

blue

14 / 30 answers

Coin flip: heads

87%

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 = 0.72 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2480.0%
tails620.0%

Coin flip · Chinese

n = 30 · H = 0.35 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2893.3%
tails26.7%

Favorite number · English

n = 30 · H = 0.21 bit · uniform baseline 13.29 bit

AnswerCountShare
72996.7%
4213.3%

Favorite number · Chinese

n = 30 · H = 0.00 bit · uniform baseline 13.29 bit

AnswerCountShare
730100.0%

Random animal · English

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

AnswerCountShare
giraffe1033.3%
elephant930.0%
lion516.7%
kangaroo516.7%
cat13.3%

Random animal · Chinese

n = 30 · H = 2.74 bit · uniform baseline 5.64 bit

AnswerCountShare
企鹅1136.7%
狮子620.0%
斑马310.0%
长颈鹿310.0%
熊猫26.7%
13.3%
蝴蝶13.3%
河马13.3%

+ 2 more answers

Random city · English

n = 30 · H = 0.88 bit · uniform baseline 5.64 bit

AnswerCountShare
paris2583.3%
tokyo310.0%
madrid13.3%
chicago13.3%

Random city · Chinese

n = 30 · H = 2.33 bit · uniform baseline 5.64 bit

AnswerCountShare
上海1136.7%
东京723.3%
巴黎516.7%
柏林413.3%
北京13.3%
伦敦13.3%
纽约13.3%

Random color · English

n = 30 · H = 1.94 bit · uniform baseline 4.91 bit

AnswerCountShare
blue1446.7%
cyan620.0%
turquoise620.0%
green310.0%
azure13.3%

Random color · Chinese

n = 30 · H = 2.06 bit · uniform baseline 4.91 bit

AnswerCountShare
1653.3%
天蓝620.0%
26.7%
深海蓝26.7%
蓝绿26.7%
靛蓝13.3%
湛蓝13.3%

Random letter · English

n = 30 · H = 2.04 bit · uniform baseline 4.70 bit

AnswerCountShare
g1136.7%
m826.7%
k826.7%
q13.3%
t13.3%
c13.3%

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 = 0.63 bit · uniform baseline 6.64 bit

AnswerCountShare
422790.0%
2413.3%
5713.3%
7313.3%

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 235B A22B?

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 235B A22B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai