Nova Pro 1.0 Behavioral Fingerprint

How Amazon's Nova Pro 1.0 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 419 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Amazon

Data generated

2026-07-08

Probe cells

14

Valid samples

419

Randomness score

56 / 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)

47

11 / 30 answers

Favorite color

purple

8 / 30 answers

Coin flip: heads

47%

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 = 1.00 bit · uniform baseline 1.00 bit

AnswerCountShare
tails1653.3%
heads1446.7%

Coin flip · Chinese

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

AnswerCountShare
tails1653.3%
heads1446.7%

Favorite number · Chinese

n = 30 · H = 0.63 bit · uniform baseline 13.29 bit

AnswerCountShare
72790.0%
213.3%
1313.3%
1613.3%

Random animal · English

n = 30 · H = 4.03 bit · uniform baseline 5.64 bit

AnswerCountShare
elephant516.7%
kangaroo310.0%
koala26.7%
zebra26.7%
panda26.7%
lion26.7%
cheetah26.7%
cow13.3%

+ 11 more answers

Random animal · Chinese

n = 30 · H = 4.44 bit · uniform baseline 5.64 bit

AnswerCountShare
413.3%
26.7%
乌龟26.7%
猴子26.7%
鳄鱼13.3%
13.3%
蓝鲸13.3%
13.3%

+ 16 more answers

Random city · English

n = 30 · H = 3.89 bit · uniform baseline 5.64 bit

AnswerCountShare
tokyo516.7%
mumbai310.0%
sydney26.7%
paris26.7%
chennai26.7%
berlin26.7%
barcelona26.7%
warsaw26.7%

+ 9 more answers

Random city · Chinese

n = 29 · H = 4.18 bit · uniform baseline 5.64 bit

AnswerCountShare
东京517.2%
名古屋26.9%
墨西哥城26.9%
大阪26.9%
悉尼26.9%
paris13.4%
纽约13.4%
多伦多13.4%

+ 13 more answers

Random color · English

n = 30 · H = 2.89 bit · uniform baseline 4.91 bit

AnswerCountShare
purple826.7%
green723.3%
blue413.3%
pink310.0%
red26.7%
orange26.7%
gray13.3%
magenta13.3%

+ 2 more answers

Random color · Chinese

n = 30 · H = 1.37 bit · uniform baseline 4.91 bit

AnswerCountShare
2376.7%
绿26.7%
13.3%
blue13.3%
13.3%
cyan13.3%
13.3%

Random letter · English

n = 30 · H = 3.96 bit · uniform baseline 4.70 bit

AnswerCountShare
y310.0%
u310.0%
j310.0%
m26.7%
k26.7%
w26.7%
g26.7%
r26.7%

+ 9 more answers

Random number 1-10 · English

n = 30 · H = 1.01 bit · uniform baseline 3.32 bit

AnswerCountShare
72480.0%
6310.0%
526.7%
413.3%

Random number 1-10 · Chinese

n = 30 · H = 0.90 bit · uniform baseline 3.32 bit

AnswerCountShare
72583.3%
326.7%
526.7%
613.3%

Random number 1-100 · English

n = 30 · H = 2.72 bit · uniform baseline 6.64 bit

AnswerCountShare
471136.7%
73723.3%
4226.7%
5726.7%
6726.7%
7426.7%
3713.3%
6313.3%

+ 2 more answers

Random number 1-100 · Chinese

n = 30 · H = 0.97 bit · uniform baseline 6.64 bit

AnswerCountShare
422583.3%
4726.7%
3713.3%
5313.3%
6713.3%

Want to verify your API really serves Nova Pro 1.0?

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 Amazon model fingerprints

Browse all 167 model fingerprints

Nova Pro 1.0 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai