GPT-5.1 Behavioral Fingerprint
How OpenAI's GPT-5.1 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 450 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
450
Randomness score
28 / 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)
57
10 / 30 answers
Favorite color
cerulean
16 / 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 = 0.84 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 22 | 73.3% |
| tails | 8 | 26.7% |
Coin flip · Chinese
n = 30 · H = 0.97 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 18 | 60.0% |
| tails | 12 | 40.0% |
Favorite number · English
n = 30 · H = 0.00 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
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 = 2.13 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| okapi | 15 | 50.0% |
| giraffe | 4 | 13.3% |
| capybara | 4 | 13.3% |
| octopus | 3 | 10.0% |
| ocelot | 2 | 6.7% |
| otter | 2 | 6.7% |
Random animal · Chinese
n = 30 · H = 2.57 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 猫 | 10 | 33.3% |
| 老虎 | 6 | 20.0% |
| 大象 | 6 | 20.0% |
| 鲸 | 2 | 6.7% |
| 长颈鹿 | 2 | 6.7% |
| 海豚 | 2 | 6.7% |
| 豹子 | 1 | 3.3% |
| 虎 | 1 | 3.3% |
Random city · English
n = 30 · H = 0.42 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| lisbon | 28 | 93.3% |
| kyoto | 1 | 3.3% |
| osaka | 1 | 3.3% |
Random city · Chinese
n = 30 · H = 2.48 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 巴黎 | 16 | 53.3% |
| 广州 | 3 | 10.0% |
| 南京 | 2 | 6.7% |
| 东京 | 2 | 6.7% |
| 里斯本 | 1 | 3.3% |
| 巴塞罗那 | 1 | 3.3% |
| 杭州 | 1 | 3.3% |
| 上海 | 1 | 3.3% |
+ 3 more answers
Random color · English
n = 30 · H = 1.44 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| cerulean | 16 | 53.3% |
| turquoise | 9 | 30.0% |
| teal | 5 | 16.7% |
Random color · Chinese
n = 30 · H = 0.21 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 29 | 96.7% |
| 绿 | 1 | 3.3% |
Random letter · English
n = 30 · H = 1.25 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| q | 21 | 70.0% |
| g | 6 | 20.0% |
| k | 2 | 6.7% |
| j | 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 = 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 = 1.93 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 57 | 10 | 33.3% |
| 47 | 9 | 30.0% |
| 73 | 7 | 23.3% |
| 37 | 4 | 13.3% |
Random number 1-100 · Chinese
n = 30 · H = 1.46 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 37 | 16 | 53.3% |
| 47 | 7 | 23.3% |
| 57 | 7 | 23.3% |
Want to verify your API really serves GPT-5.1?
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.