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
| Answer | Count | Share |
|---|---|---|
| heads | 25 | 86.2% |
| tails | 4 | 13.8% |
Coin flip · Chinese
n = 29 · H = 0.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 29 | 100.0% |
Favorite number · English
n = 30 · H = 0.95 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 19 | 63.3% |
| 42 | 11 | 36.7% |
Favorite number · Chinese
n = 30 · H = 1.27 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 16 | 53.3% |
| 8 | 12 | 40.0% |
| 42 | 2 | 6.7% |
Random animal · English
n = 28 · H = 1.98 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| platypus | 18 | 64.3% |
| elephant | 2 | 7.1% |
| panther | 2 | 7.1% |
| jaguar | 1 | 3.6% |
| hippopotamus | 1 | 3.6% |
| capybara | 1 | 3.6% |
| giraffe | 1 | 3.6% |
| squirrel | 1 | 3.6% |
+ 1 more answers
Random animal · Chinese
n = 29 · H = 2.57 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 猫 | 8 | 27.6% |
| 熊猫 | 7 | 24.1% |
| 企鹅 | 4 | 13.8% |
| 狐狸 | 4 | 13.8% |
| 长颈鹿 | 3 | 10.3% |
| 斑马 | 2 | 6.9% |
| 鸭嘴兽 | 1 | 3.4% |
Random city · English
n = 27 · H = 1.58 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| kyoto | 16 | 59.3% |
| springfield | 5 | 18.5% |
| tokyo | 4 | 14.8% |
| dubai | 2 | 7.4% |
Random city · Chinese
n = 29 · H = 2.55 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 东京 | 14 | 48.3% |
| 北京 | 3 | 10.3% |
| 巴黎 | 3 | 10.3% |
| 成都 | 2 | 6.9% |
| 基多 | 2 | 6.9% |
| 斯德哥尔摩 | 1 | 3.4% |
| 莫斯科 | 1 | 3.4% |
| 上海 | 1 | 3.4% |
+ 2 more answers
Random color · English
n = 28 · H = 2.46 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| cerulean | 9 | 32.1% |
| blue | 7 | 25.0% |
| teal | 4 | 14.3% |
| cyan | 3 | 10.7% |
| azure | 3 | 10.7% |
| turquoise | 1 | 3.6% |
| magenta | 1 | 3.6% |
Random color · Chinese
n = 27 · H = 1.83 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 青 | 13 | 48.1% |
| 蓝 | 8 | 29.6% |
| 紫 | 3 | 11.1% |
| 绿 | 2 | 7.4% |
| 紫罗兰 | 1 | 3.7% |
Random letter · English
n = 28 · H = 1.06 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| q | 22 | 78.6% |
| k | 3 | 10.7% |
| r | 2 | 7.1% |
| j | 1 | 3.6% |
Random number 1-10 · English
n = 30 · H = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
Random number 1-10 · Chinese
n = 29 · H = 0.36 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 27 | 93.1% |
| 4 | 2 | 6.9% |
Random number 1-100 · English
n = 29 · H = 0.58 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 25 | 86.2% |
| 73 | 4 | 13.8% |
Random number 1-100 · Chinese
n = 29 · H = 0.58 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 25 | 86.2% |
| 73 | 4 | 13.8% |
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 endpointData 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.