Qwen3 30B A3B Instruct 2507 Behavioral Fingerprint

How Qwen's Qwen3 30B A3B Instruct 2507 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 439 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

439

Randomness score

19 / 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

30 / 30 answers

Favorite color

blue

29 / 30 answers

Coin flip: heads

86%

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 = 29 · H = 0.85 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2172.4%
tails827.6%

Coin flip · Chinese

n = 29 · H = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads29100.0%

Favorite number · English

n = 28 · H = 0.00 bit · uniform baseline 13.29 bit

AnswerCountShare
728100.0%

Favorite number · Chinese

n = 29 · H = 0.00 bit · uniform baseline 13.29 bit

AnswerCountShare
729100.0%

Random animal · English

n = 29 · H = 1.73 bit · uniform baseline 5.64 bit

AnswerCountShare
lion1758.6%
elephant517.2%
tiger310.3%
dog310.3%
penguin13.4%

Random animal · Chinese

n = 30 · H = 1.78 bit · uniform baseline 5.64 bit

AnswerCountShare
老虎1756.7%
狮子723.3%
310.0%
tiger13.3%
熊猫13.3%
13.3%

Random city · English

n = 30 · H = 2.32 bit · uniform baseline 5.64 bit

AnswerCountShare
paris1446.7%
sydney723.3%
tokyo310.0%
chicago13.3%
melbourne13.3%
london13.3%
amsterdam13.3%
lisbon13.3%

+ 1 more answers

Random city · Chinese

n = 29 · H = 1.90 bit · uniform baseline 5.64 bit

AnswerCountShare
上海1448.3%
巴黎931.0%
北京26.9%
纽约26.9%
柏林13.4%
杭州13.4%

Random color · English

n = 30 · H = 0.21 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2996.7%
green13.3%

Random color · Chinese

n = 29 · H = 0.36 bit · uniform baseline 4.91 bit

AnswerCountShare
2793.1%
绿26.9%

Random letter · English

n = 30 · H = 2.05 bit · uniform baseline 4.70 bit

AnswerCountShare
m1860.0%
k310.0%
a26.7%
b26.7%
g26.7%
d13.3%
e13.3%
c13.3%

Random number 1-10 · English

n = 29 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
729100.0%

Random number 1-10 · Chinese

n = 28 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
728100.0%

Random number 1-100 · English

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

AnswerCountShare
4230100.0%

Random number 1-100 · Chinese

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

AnswerCountShare
422996.7%
6713.3%

Want to verify your API really serves Qwen3 30B A3B Instruct 2507?

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 30B A3B Instruct 2507 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai