GLM 5 Turbo Behavioral Fingerprint
How Z.ai's GLM 5 Turbo 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
17 / 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
30 / 30 answers
Favorite color
magenta
14 / 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 = 29 · H = 0.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 29 | 100.0% |
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 = 0.72 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 24 | 80.0% |
| 7 | 6 | 20.0% |
Favorite number · Chinese
n = 29 · H = 0.22 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 28 | 96.6% |
| 3 | 1 | 3.4% |
Random animal · English
n = 29 · H = 0.80 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| giraffe | 22 | 75.9% |
| elephant | 7 | 24.1% |
Random animal · Chinese
n = 30 · H = 3.01 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 老虎 | 7 | 23.3% |
| 猫 | 5 | 16.7% |
| 考拉 | 5 | 16.7% |
| 狗 | 4 | 13.3% |
| 长颈鹿 | 2 | 6.7% |
| 熊猫 | 2 | 6.7% |
| 大象 | 2 | 6.7% |
| 猎豹 | 1 | 3.3% |
+ 2 more answers
Random city · English
n = 29 · H = 2.28 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| chicago | 9 | 31.0% |
| tokyo | 9 | 31.0% |
| berlin | 5 | 17.2% |
| topeka | 2 | 6.9% |
| paris | 2 | 6.9% |
| london | 2 | 6.9% |
Random city · Chinese
n = 29 · H = 2.23 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 巴黎 | 15 | 51.7% |
| 东京 | 5 | 17.2% |
| 上海 | 2 | 6.9% |
| 重庆 | 2 | 6.9% |
| 深圳 | 2 | 6.9% |
| 杭州 | 1 | 3.4% |
| 大阪 | 1 | 3.4% |
| 柏林 | 1 | 3.4% |
Random color · English
n = 29 · H = 2.03 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| magenta | 14 | 48.3% |
| blue | 8 | 27.6% |
| green | 3 | 10.3% |
| cyan | 1 | 3.4% |
| mauve | 1 | 3.4% |
| crimson | 1 | 3.4% |
| turquoise | 1 | 3.4% |
Random color · Chinese
n = 29 · H = 1.07 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 21 | 72.4% |
| 绿 | 6 | 20.7% |
| 红 | 2 | 6.9% |
Random letter · English
n = 29 · H = 1.44 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| g | 16 | 55.2% |
| k | 7 | 24.1% |
| q | 6 | 20.7% |
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 = 30 · H = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
Random number 1-100 · English
n = 30 · H = 0.00 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 30 | 100.0% |
Random number 1-100 · Chinese
n = 30 · H = 0.00 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 30 | 100.0% |
Want to verify your API really serves GLM 5 Turbo?
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.