GPT-4.1 Nano Behavioral Fingerprint
How OpenAI's GPT-4.1 Nano answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 444 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
OpenAI
Data generated
2026-07-08
Probe cells
15
Valid samples
444
Randomness score
33 / 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)
47
10 / 30 answers
Favorite color
blue
9 / 30 answers
Coin flip: heads
65%
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 = 0.78 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 23 | 76.7% |
| tails | 7 | 23.3% |
Favorite number · English
n = 25 · H = 0.40 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 23 | 92.0% |
| 42 | 2 | 8.0% |
Favorite number · Chinese
n = 30 · H = 0.00 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
Random animal · English
n = 30 · H = 2.47 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| elephant | 11 | 36.7% |
| giraffe | 6 | 20.0% |
| koala | 6 | 20.0% |
| otter | 2 | 6.7% |
| tiger | 2 | 6.7% |
| leonardo | 1 | 3.3% |
| jaguar | 1 | 3.3% |
| kangaroo | 1 | 3.3% |
Random animal · Chinese
n = 30 · H = 2.65 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 猫 | 10 | 33.3% |
| 虎 | 9 | 30.0% |
| 象 | 2 | 6.7% |
| 鹰 | 2 | 6.7% |
| 豚 | 2 | 6.7% |
| 狮子 | 1 | 3.3% |
| 豹 | 1 | 3.3% |
| 斑马 | 1 | 3.3% |
+ 2 more answers
Random city · English
n = 30 · H = 3.24 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| lagos | 10 | 33.3% |
| kyoto | 4 | 13.3% |
| tokyo | 3 | 10.0% |
| oslo | 2 | 6.7% |
| dublin | 2 | 6.7% |
| lisbon | 1 | 3.3% |
| cairo | 1 | 3.3% |
| helsinki | 1 | 3.3% |
+ 6 more answers
Random city · Chinese
n = 30 · H = 0.67 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 东京 | 26 | 86.7% |
| 巴黎 | 3 | 10.0% |
| 京都 | 1 | 3.3% |
Random color · English
n = 30 · H = 2.75 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 9 | 30.0% |
| violet | 6 | 20.0% |
| azure | 4 | 13.3% |
| turquoise | 3 | 10.0% |
| vermilion | 2 | 6.7% |
| crimson | 2 | 6.7% |
| magenta | 2 | 6.7% |
| cyan | 2 | 6.7% |
Random color · Chinese
n = 30 · H = 0.00 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 30 | 100.0% |
Random letter · English
n = 30 · H = 1.82 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| m | 16 | 53.3% |
| k | 8 | 26.7% |
| q | 3 | 10.0% |
| g | 1 | 3.3% |
| h | 1 | 3.3% |
| n | 1 | 3.3% |
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 = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 29 | 100.0% |
Random number 1-100 · English
n = 30 · H = 1.83 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 47 | 10 | 33.3% |
| 57 | 10 | 33.3% |
| 73 | 8 | 26.7% |
| 42 | 2 | 6.7% |
Random number 1-100 · Chinese
n = 30 · H = 2.54 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 12 | 40.0% |
| 73 | 5 | 16.7% |
| 37 | 3 | 10.0% |
| 47 | 3 | 10.0% |
| 57 | 3 | 10.0% |
| 56 | 2 | 6.7% |
| 45 | 1 | 3.3% |
| 58 | 1 | 3.3% |
Want to verify your API really serves GPT-4.1 Nano?
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.