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
| Answer | Count | Share |
|---|---|---|
| heads | 28 | 100.0% |
Coin flip · Chinese
n = 30 · H = 0.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 30 | 100.0% |
Favorite number · English
n = 28 · H = 0.94 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 18 | 64.3% |
| 42 | 10 | 35.7% |
Favorite number · Chinese
n = 29 · H = 1.24 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 21 | 72.4% |
| 8 | 4 | 13.8% |
| 42 | 3 | 10.3% |
| 6 | 1 | 3.4% |
Random animal · English
n = 30 · H = 1.80 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| platypus | 20 | 66.7% |
| elephant | 3 | 10.0% |
| tiger | 2 | 6.7% |
| hippo | 1 | 3.3% |
| wombat | 1 | 3.3% |
| pangolin | 1 | 3.3% |
| capybara | 1 | 3.3% |
| sloth | 1 | 3.3% |
Random animal · Chinese
n = 28 · H = 2.87 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 长颈鹿 | 8 | 28.6% |
| 熊猫 | 6 | 21.4% |
| 猫 | 3 | 10.7% |
| 老虎 | 2 | 7.1% |
| 树懒 | 2 | 7.1% |
| 袋鼠 | 2 | 7.1% |
| 水豚 | 2 | 7.1% |
| 鸭嘴兽 | 2 | 7.1% |
+ 1 more answers
Random city · English
n = 29 · H = 2.20 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| paris | 15 | 51.7% |
| kyoto | 5 | 17.2% |
| tokyo | 3 | 10.3% |
| oslo | 2 | 6.9% |
| london | 1 | 3.4% |
| madrid | 1 | 3.4% |
| springfield | 1 | 3.4% |
| austin | 1 | 3.4% |
Random city · Chinese
n = 28 · H = 2.66 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 东京 | 14 | 50.0% |
| 巴黎 | 3 | 10.7% |
| 上海 | 2 | 7.1% |
| 横滨 | 1 | 3.6% |
| 沈阳 | 1 | 3.6% |
| 马德里 | 1 | 3.6% |
| 伦敦 | 1 | 3.6% |
| 堪培拉 | 1 | 3.6% |
+ 4 more answers
Random color · English
n = 29 · H = 2.00 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 15 | 51.7% |
| cyan | 5 | 17.2% |
| cerulean | 4 | 13.8% |
| teal | 3 | 10.3% |
| turquoise | 1 | 3.4% |
| magenta | 1 | 3.4% |
Random color · Chinese
n = 29 · H = 1.95 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 紫 | 12 | 41.4% |
| 蓝 | 7 | 24.1% |
| 青 | 7 | 24.1% |
| 靛青 | 2 | 6.9% |
| 红 | 1 | 3.4% |
Random letter · English
n = 28 · H = 1.35 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| q | 18 | 64.3% |
| k | 7 | 25.0% |
| g | 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 = 30 · H = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
Random number 1-100 · English
n = 28 · H = 0.00 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 28 | 100.0% |
Random number 1-100 · Chinese
n = 28 · H = 0.44 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 26 | 92.9% |
| 47 | 1 | 3.6% |
| 57 | 1 | 3.6% |
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 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.