GLM 5 Behavioral Fingerprint

How Z.ai's GLM 5 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 432 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

432

Randomness score

20 / 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 / 28 answers

Favorite color

blue

15 / 29 answers

Coin flip: heads

100%

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 = 28 · H = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads28100.0%

Coin flip · Chinese

n = 30 · H = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads30100.0%

Favorite number · English

n = 28 · H = 0.94 bit · uniform baseline 13.29 bit

AnswerCountShare
71864.3%
421035.7%

Favorite number · Chinese

n = 29 · H = 1.24 bit · uniform baseline 13.29 bit

AnswerCountShare
72172.4%
8413.8%
42310.3%
613.4%

Random animal · English

n = 30 · H = 1.80 bit · uniform baseline 5.64 bit

AnswerCountShare
platypus2066.7%
elephant310.0%
tiger26.7%
hippo13.3%
wombat13.3%
pangolin13.3%
capybara13.3%
sloth13.3%

Random animal · Chinese

n = 28 · H = 2.87 bit · uniform baseline 5.64 bit

AnswerCountShare
长颈鹿828.6%
熊猫621.4%
310.7%
老虎27.1%
树懒27.1%
袋鼠27.1%
水豚27.1%
鸭嘴兽27.1%

+ 1 more answers

Random city · English

n = 29 · H = 2.20 bit · uniform baseline 5.64 bit

AnswerCountShare
paris1551.7%
kyoto517.2%
tokyo310.3%
oslo26.9%
london13.4%
madrid13.4%
springfield13.4%
austin13.4%

Random city · Chinese

n = 28 · H = 2.66 bit · uniform baseline 5.64 bit

AnswerCountShare
东京1450.0%
巴黎310.7%
上海27.1%
横滨13.6%
沈阳13.6%
马德里13.6%
伦敦13.6%
堪培拉13.6%

+ 4 more answers

Random color · English

n = 29 · H = 2.00 bit · uniform baseline 4.91 bit

AnswerCountShare
blue1551.7%
cyan517.2%
cerulean413.8%
teal310.3%
turquoise13.4%
magenta13.4%

Random color · Chinese

n = 29 · H = 1.95 bit · uniform baseline 4.91 bit

AnswerCountShare
1241.4%
724.1%
724.1%
靛青26.9%
13.4%

Random letter · English

n = 28 · H = 1.35 bit · uniform baseline 4.70 bit

AnswerCountShare
q1864.3%
k725.0%
g27.1%
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 = 30 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-100 · English

n = 28 · H = 0.00 bit · uniform baseline 6.64 bit

AnswerCountShare
4228100.0%

Random number 1-100 · Chinese

n = 28 · H = 0.44 bit · uniform baseline 6.64 bit

AnswerCountShare
422692.9%
4713.6%
5713.6%

Want to verify your API really serves GLM 5?

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