GLM 5.2 Behavioral Fingerprint

How Z.ai's GLM 5.2 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 431 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Z.ai

Data generated

2026-07-08

Probe cells

15

Valid samples

431

Randomness score

24 / 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 / 29 answers

Favorite color

cerulean

9 / 28 answers

Coin flip: heads

93%

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 = 0.58 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2586.2%
tails413.8%

Coin flip · Chinese

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

AnswerCountShare
heads29100.0%

Favorite number · English

n = 30 · H = 0.95 bit · uniform baseline 13.29 bit

AnswerCountShare
71963.3%
421136.7%

Favorite number · Chinese

n = 30 · H = 1.27 bit · uniform baseline 13.29 bit

AnswerCountShare
71653.3%
81240.0%
4226.7%

Random animal · English

n = 28 · H = 1.98 bit · uniform baseline 5.64 bit

AnswerCountShare
platypus1864.3%
elephant27.1%
panther27.1%
jaguar13.6%
hippopotamus13.6%
capybara13.6%
giraffe13.6%
squirrel13.6%

+ 1 more answers

Random animal · Chinese

n = 29 · H = 2.57 bit · uniform baseline 5.64 bit

AnswerCountShare
827.6%
熊猫724.1%
企鹅413.8%
狐狸413.8%
长颈鹿310.3%
斑马26.9%
鸭嘴兽13.4%

Random city · English

n = 27 · H = 1.58 bit · uniform baseline 5.64 bit

AnswerCountShare
kyoto1659.3%
springfield518.5%
tokyo414.8%
dubai27.4%

Random city · Chinese

n = 29 · H = 2.55 bit · uniform baseline 5.64 bit

AnswerCountShare
东京1448.3%
北京310.3%
巴黎310.3%
成都26.9%
基多26.9%
斯德哥尔摩13.4%
莫斯科13.4%
上海13.4%

+ 2 more answers

Random color · English

n = 28 · H = 2.46 bit · uniform baseline 4.91 bit

AnswerCountShare
cerulean932.1%
blue725.0%
teal414.3%
cyan310.7%
azure310.7%
turquoise13.6%
magenta13.6%

Random color · Chinese

n = 27 · H = 1.83 bit · uniform baseline 4.91 bit

AnswerCountShare
1348.1%
829.6%
311.1%
绿27.4%
紫罗兰13.7%

Random letter · English

n = 28 · H = 1.06 bit · uniform baseline 4.70 bit

AnswerCountShare
q2278.6%
k310.7%
r27.1%
j13.6%

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 = 29 · H = 0.36 bit · uniform baseline 3.32 bit

AnswerCountShare
72793.1%
426.9%

Random number 1-100 · English

n = 29 · H = 0.58 bit · uniform baseline 6.64 bit

AnswerCountShare
422586.2%
73413.8%

Random number 1-100 · Chinese

n = 29 · H = 0.58 bit · uniform baseline 6.64 bit

AnswerCountShare
422586.2%
73413.8%

Want to verify your API really serves GLM 5.2?

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 Z.ai model fingerprints

Browse all 167 model fingerprints

GLM 5.2 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai