GLM 4.7 Behavioral Fingerprint

How Z.ai's GLM 4.7 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 441 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

441

Randomness score

37 / 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

28 / 30 answers

Favorite color

blue

8 / 30 answers

Coin flip: heads

78%

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 = 0.98 bit · uniform baseline 1.00 bit

AnswerCountShare
heads1758.6%
tails1241.4%

Coin flip · Chinese

n = 29 · H = 0.22 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2896.6%
tails13.4%

Favorite number · English

n = 30 · H = 0.42 bit · uniform baseline 13.29 bit

AnswerCountShare
422893.3%
013.3%
713.3%

Favorite number · Chinese

n = 29 · H = 1.09 bit · uniform baseline 13.29 bit

AnswerCountShare
421965.5%
7931.0%
813.4%

Random animal · English

n = 28 · H = 2.43 bit · uniform baseline 5.64 bit

AnswerCountShare
giraffe1139.3%
elephant932.1%
tiger13.6%
echidna13.6%
dog13.6%
squid13.6%
platypus13.6%
kangaroo13.6%

+ 2 more answers

Random animal · Chinese

n = 29 · H = 3.11 bit · uniform baseline 5.64 bit

AnswerCountShare
大象724.1%
熊猫620.7%
长颈鹿310.3%
310.3%
猎豹26.9%
河马26.9%
26.9%
斑马13.4%

+ 3 more answers

Random city · English

n = 29 · H = 2.72 bit · uniform baseline 5.64 bit

AnswerCountShare
tokyo931.0%
london620.7%
berlin413.8%
paris413.8%
kyoto26.9%
sydney13.4%
seattle13.4%
manchester13.4%

+ 1 more answers

Random city · Chinese

n = 30 · H = 2.87 bit · uniform baseline 5.64 bit

AnswerCountShare
巴黎826.7%
东京620.0%
上海620.0%
北京26.7%
柏林26.7%
伦敦26.7%
马德里13.3%
伊斯坦布尔13.3%

+ 2 more answers

Random color · English

n = 30 · H = 3.11 bit · uniform baseline 4.91 bit

AnswerCountShare
blue826.7%
turquoise516.7%
cyan310.0%
cerulean310.0%
azure310.0%
purple26.7%
teal26.7%
chartreuse13.3%

+ 3 more answers

Random color · Chinese

n = 30 · H = 2.05 bit · uniform baseline 4.91 bit

AnswerCountShare
1653.3%
绿516.7%
413.3%
26.7%
天蓝13.3%
靛蓝13.3%
13.3%

Random letter · English

n = 30 · H = 2.26 bit · uniform baseline 4.70 bit

AnswerCountShare
k1136.7%
g930.0%
q413.3%
p310.0%
m13.3%
j13.3%
r13.3%

Random number 1-10 · English

n = 29 · H = 0.83 bit · uniform baseline 3.32 bit

AnswerCountShare
72482.8%
4310.3%
326.9%

Random number 1-10 · Chinese

n = 29 · H = 0.83 bit · uniform baseline 3.32 bit

AnswerCountShare
72482.8%
4310.3%
326.9%

Random number 1-100 · English

n = 30 · H = 0.42 bit · uniform baseline 6.64 bit

AnswerCountShare
422893.3%
3713.3%
5813.3%

Random number 1-100 · Chinese

n = 30 · H = 0.88 bit · uniform baseline 6.64 bit

AnswerCountShare
422583.3%
37310.0%
5813.3%
7313.3%

Want to verify your API really serves GLM 4.7?

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