GPT-5.5 Behavioral Fingerprint
How OpenAI's GPT-5.5 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
27 / 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
19 / 30 answers
Favorite color
purple
15 / 30 answers
Coin flip: heads
42%
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 = 0.35 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| tails | 28 | 93.3% |
| heads | 2 | 6.7% |
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 = 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 = 2.62 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| giraffe | 12 | 40.0% |
| pangolin | 5 | 16.7% |
| capybara | 4 | 13.3% |
| platypus | 2 | 6.7% |
| tapir | 2 | 6.7% |
| otter | 2 | 6.7% |
| koala | 1 | 3.3% |
| ocelot | 1 | 3.3% |
+ 1 more answers
Random animal · Chinese
n = 30 · H = 2.62 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 海豚 | 12 | 40.0% |
| 考拉 | 6 | 20.0% |
| 袋鼠 | 4 | 13.3% |
| 水豚 | 2 | 6.7% |
| 斑马 | 1 | 3.3% |
| 鹦鹉 | 1 | 3.3% |
| 长颈鹿 | 1 | 3.3% |
| 水獭 | 1 | 3.3% |
+ 2 more answers
Random city · English
n = 30 · H = 2.51 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| valencia | 9 | 30.0% |
| lisbon | 8 | 26.7% |
| kyoto | 6 | 20.0% |
| tokyo | 2 | 6.7% |
| copenhagen | 2 | 6.7% |
| quito | 1 | 3.3% |
| reykjavik | 1 | 3.3% |
| barcelona | 1 | 3.3% |
Random city · Chinese
n = 30 · H = 3.87 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 里斯本 | 6 | 20.0% |
| 布拉格 | 3 | 10.0% |
| 赫尔辛基 | 3 | 10.0% |
| 东京 | 2 | 6.7% |
| 哥本哈根 | 2 | 6.7% |
| 大阪 | 2 | 6.7% |
| 奥斯陆 | 1 | 3.3% |
| 上海 | 1 | 3.3% |
+ 10 more answers
Random color · English
n = 30 · H = 1.00 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| purple | 15 | 50.0% |
| blue | 15 | 50.0% |
Random color · Chinese
n = 30 · H = 0.77 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 25 | 83.3% |
| 紫 | 4 | 13.3% |
| 绿 | 1 | 3.3% |
Random letter · English
n = 30 · H = 0.47 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| q | 27 | 90.0% |
| k | 3 | 10.0% |
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 = 1.47 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 47 | 19 | 63.3% |
| 42 | 6 | 20.0% |
| 57 | 3 | 10.0% |
| 37 | 2 | 6.7% |
Random number 1-100 · Chinese
n = 30 · H = 0.85 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 47 | 24 | 80.0% |
| 37 | 5 | 16.7% |
| 42 | 1 | 3.3% |
Want to verify your API really serves GPT-5.5?
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.