GPT-4o (2024-08-06) Behavioral Fingerprint
How OpenAI's GPT-4o (2024-08-06) answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 438 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
438
Randomness score
38 / 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
11 / 30 answers
Favorite color
blue
16 / 30 answers
Coin flip: heads
70%
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 = 0.95 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 19 | 63.3% |
| tails | 11 | 36.7% |
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 = 18 · H = 1.68 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 10 | 55.6% |
| 42 | 5 | 27.8% |
| 1 | 1 | 5.6% |
| 10 | 1 | 5.6% |
| 17 | 1 | 5.6% |
Favorite number · Chinese
n = 30 · H = 0.47 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 27 | 90.0% |
| 42 | 3 | 10.0% |
Random animal · English
n = 30 · H = 1.38 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| elephant | 21 | 70.0% |
| tiger | 5 | 16.7% |
| penguin | 2 | 6.7% |
| giraffe | 1 | 3.3% |
| dolphin | 1 | 3.3% |
Random animal · Chinese
n = 30 · H = 3.74 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 企鹅 | 4 | 13.3% |
| 大象 | 3 | 10.0% |
| 长颈鹿 | 3 | 10.0% |
| 象 | 3 | 10.0% |
| 狮子 | 3 | 10.0% |
| 猫 | 2 | 6.7% |
| 熊猫 | 2 | 6.7% |
| 狐狸 | 2 | 6.7% |
+ 7 more answers
Random city · English
n = 30 · H = 1.05 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| tokyo | 23 | 76.7% |
| paris | 5 | 16.7% |
| kyoto | 1 | 3.3% |
| toronto | 1 | 3.3% |
Random city · Chinese
n = 30 · H = 1.82 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 东京 | 16 | 53.3% |
| 巴黎 | 9 | 30.0% |
| 巴塞罗那 | 1 | 3.3% |
| 伦敦 | 1 | 3.3% |
| 纽约 | 1 | 3.3% |
| 上海 | 1 | 3.3% |
| 都柏林 | 1 | 3.3% |
Random color · English
n = 30 · H = 1.82 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 16 | 53.3% |
| azure | 8 | 26.7% |
| cerulean | 3 | 10.0% |
| teal | 1 | 3.3% |
| green | 1 | 3.3% |
| turquoise | 1 | 3.3% |
Random color · Chinese
n = 30 · H = 0.42 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 28 | 93.3% |
| 靛青 | 1 | 3.3% |
| 绿 | 1 | 3.3% |
Random letter · English
n = 30 · H = 2.90 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| g | 10 | 33.3% |
| m | 6 | 20.0% |
| k | 3 | 10.0% |
| j | 3 | 10.0% |
| f | 2 | 6.7% |
| s | 1 | 3.3% |
| b | 1 | 3.3% |
| w | 1 | 3.3% |
+ 3 more answers
Random number 1-10 · English
n = 30 · H = 0.99 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 23 | 76.7% |
| 5 | 5 | 16.7% |
| 8 | 2 | 6.7% |
Random number 1-10 · Chinese
n = 30 · H = 1.11 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 24 | 80.0% |
| 5 | 2 | 6.7% |
| 6 | 2 | 6.7% |
| 3 | 1 | 3.3% |
| 4 | 1 | 3.3% |
Random number 1-100 · English
n = 30 · H = 2.52 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 57 | 11 | 36.7% |
| 42 | 8 | 26.7% |
| 37 | 3 | 10.0% |
| 47 | 3 | 10.0% |
| 17 | 1 | 3.3% |
| 67 | 1 | 3.3% |
| 73 | 1 | 3.3% |
| 74 | 1 | 3.3% |
+ 1 more answers
Random number 1-100 · Chinese
n = 30 · H = 1.89 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 16 | 53.3% |
| 57 | 7 | 23.3% |
| 27 | 3 | 10.0% |
| 37 | 2 | 6.7% |
| 56 | 1 | 3.3% |
| 58 | 1 | 3.3% |
Want to verify your API really serves GPT-4o (2024-08-06)?
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.