GLM 4.7 Flash Behavioral Fingerprint
How Z.ai's GLM 4.7 Flash answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 446 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
446
Randomness score
55 / 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
20 / 30 answers
Favorite color
blue
8 / 30 answers
Coin flip: heads
67%
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 = 30 · H = 1.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 16 | 53.3% |
| tails | 14 | 46.7% |
Coin flip · Chinese
n = 30 · H = 0.72 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 24 | 80.0% |
| tails | 6 | 20.0% |
Favorite number · English
n = 29 · H = 1.17 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 16 | 55.2% |
| 7 | 12 | 41.4% |
| 13 | 1 | 3.4% |
Favorite number · Chinese
n = 29 · H = 2.44 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 12 | 41.4% |
| 1 | 6 | 20.7% |
| 3 | 5 | 17.2% |
| 0 | 1 | 3.4% |
| 8 | 1 | 3.4% |
| 9 | 1 | 3.4% |
| 10 | 1 | 3.4% |
| 17 | 1 | 3.4% |
+ 1 more answers
Random animal · English
n = 30 · H = 3.81 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| tiger | 6 | 20.0% |
| giraffe | 3 | 10.0% |
| penguin | 3 | 10.0% |
| sloth | 2 | 6.7% |
| duck | 2 | 6.7% |
| koala | 2 | 6.7% |
| lion | 2 | 6.7% |
| panda | 1 | 3.3% |
+ 9 more answers
Random animal · Chinese
n = 30 · H = 3.81 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 猫 | 6 | 20.0% |
| 老虎 | 3 | 10.0% |
| 熊猫 | 3 | 10.0% |
| 猩猩 | 2 | 6.7% |
| 大象 | 2 | 6.7% |
| 斑马 | 2 | 6.7% |
| 狮子 | 2 | 6.7% |
| 鸭子 | 1 | 3.3% |
+ 9 more answers
Random city · English
n = 30 · H = 2.65 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| paris | 13 | 43.3% |
| tokyo | 5 | 16.7% |
| london | 4 | 13.3% |
| seattle | 1 | 3.3% |
| acapulco | 1 | 3.3% |
| zermatt | 1 | 3.3% |
| chicago | 1 | 3.3% |
| dubai | 1 | 3.3% |
+ 3 more answers
Random city · Chinese
n = 30 · H = 3.35 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 东京 | 10 | 33.3% |
| 巴黎 | 5 | 16.7% |
| 罗马 | 2 | 6.7% |
| kolkata | 1 | 3.3% |
| 伊斯坦布尔 | 1 | 3.3% |
| 北京 | 1 | 3.3% |
| tokyo | 1 | 3.3% |
| 迪拜 | 1 | 3.3% |
+ 8 more answers
Random color · English
n = 30 · H = 3.52 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 8 | 26.7% |
| purple | 5 | 16.7% |
| black | 2 | 6.7% |
| indigo | 2 | 6.7% |
| teal | 2 | 6.7% |
| puce | 1 | 3.3% |
| neon | 1 | 3.3% |
| lilac | 1 | 3.3% |
+ 8 more answers
Random color · Chinese
n = 29 · H = 3.17 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 9 | 31.0% |
| 紫 | 5 | 17.2% |
| 绿 | 3 | 10.3% |
| 红 | 2 | 6.9% |
| 青 | 2 | 6.9% |
| 紫罗兰 | 1 | 3.4% |
| teal | 1 | 3.4% |
| 紫色的 | 1 | 3.4% |
+ 5 more answers
Random letter · English
n = 30 · H = 2.88 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| z | 11 | 36.7% |
| x | 4 | 13.3% |
| c | 3 | 10.0% |
| k | 2 | 6.7% |
| m | 2 | 6.7% |
| g | 2 | 6.7% |
| e | 2 | 6.7% |
| r | 2 | 6.7% |
+ 2 more answers
Random number 1-10 · English
n = 30 · H = 1.51 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 20 | 66.7% |
| 5 | 5 | 16.7% |
| 4 | 2 | 6.7% |
| 8 | 2 | 6.7% |
| 6 | 1 | 3.3% |
Random number 1-10 · Chinese
n = 29 · H = 2.21 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 12 | 41.4% |
| 4 | 6 | 20.7% |
| 5 | 5 | 17.2% |
| 6 | 3 | 10.3% |
| 8 | 2 | 6.9% |
| 3 | 1 | 3.4% |
Random number 1-100 · English
n = 30 · H = 1.69 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 20 | 66.7% |
| 73 | 4 | 13.3% |
| 87 | 2 | 6.7% |
| 7 | 1 | 3.3% |
| 57 | 1 | 3.3% |
| 63 | 1 | 3.3% |
| 72 | 1 | 3.3% |
Random number 1-100 · Chinese
n = 30 · H = 3.28 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 11 | 36.7% |
| 67 | 3 | 10.0% |
| 53 | 2 | 6.7% |
| 72 | 2 | 6.7% |
| 73 | 2 | 6.7% |
| 6 | 1 | 3.3% |
| 7 | 1 | 3.3% |
| 33 | 1 | 3.3% |
+ 7 more answers
Want to verify your API really serves GLM 4.7 Flash?
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.