GPT-3.5 Turbo Instruct Behavioral Fingerprint
How OpenAI's GPT-3.5 Turbo Instruct answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 380 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
OpenAI
Data generated
2026-07-08
Probe cells
14
Valid samples
380
Randomness score
51 / 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
5 / 30 answers
Favorite color
blue
18 / 29 answers
Coin flip: heads
83%
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 · Chinese
n = 29 · H = 0.66 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 24 | 82.8% |
| tails | 5 | 17.2% |
Favorite number · English
n = 18 · H = 2.21 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 9 | 50.0% |
| 42 | 3 | 16.7% |
| 19 | 2 | 11.1% |
| 5 | 1 | 5.6% |
| 27 | 1 | 5.6% |
| 100 | 1 | 5.6% |
| 123 | 1 | 5.6% |
Favorite number · Chinese
n = 13 · H = 2.19 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 5 | 38.5% |
| 5 | 4 | 30.8% |
| 0 | 1 | 7.7% |
| 4 | 1 | 7.7% |
| 9 | 1 | 7.7% |
| 11 | 1 | 7.7% |
Random animal · English
n = 28 · H = 3.41 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| lion | 6 | 21.4% |
| elephant | 4 | 14.3% |
| dog | 3 | 10.7% |
| cat | 3 | 10.7% |
| turtle | 2 | 7.1% |
| penguin | 2 | 7.1% |
| tiger | 2 | 7.1% |
| koala | 1 | 3.6% |
+ 5 more answers
Random animal · Chinese
n = 29 · H = 2.50 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 猫 | 10 | 34.5% |
| 狗 | 9 | 31.0% |
| 熊 | 3 | 10.3% |
| 猴子 | 2 | 6.9% |
| 狮子 | 1 | 3.4% |
| 翼龙 | 1 | 3.4% |
| 老虎 | 1 | 3.4% |
| 鲸鱼 | 1 | 3.4% |
+ 1 more answers
Random city · English
n = 27 · H = 3.29 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| chicago | 5 | 18.5% |
| london | 4 | 14.8% |
| new | 4 | 14.8% |
| paris | 4 | 14.8% |
| berlin | 2 | 7.4% |
| seattle | 2 | 7.4% |
| nairobi | 1 | 3.7% |
| denver | 1 | 3.7% |
+ 4 more answers
Random city · Chinese
n = 29 · H = 2.52 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 北京 | 13 | 44.8% |
| 上海 | 5 | 17.2% |
| 纽约 | 4 | 13.8% |
| 非洲 | 1 | 3.4% |
| 新加坡 | 1 | 3.4% |
| 巴黎 | 1 | 3.4% |
| 哥本哈根 | 1 | 3.4% |
| 洛杉矶 | 1 | 3.4% |
+ 2 more answers
Random color · English
n = 29 · H = 1.73 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 18 | 62.1% |
| red | 5 | 17.2% |
| purple | 2 | 6.9% |
| yellow | 2 | 6.9% |
| green | 1 | 3.4% |
| saffron | 1 | 3.4% |
Random color · Chinese
n = 30 · H = 1.80 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 红 | 14 | 46.7% |
| 蓝 | 11 | 36.7% |
| 紫 | 2 | 6.7% |
| 黑 | 1 | 3.3% |
| 粉红 | 1 | 3.3% |
| 绿 | 1 | 3.3% |
Random letter · English
n = 28 · H = 3.32 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| q | 8 | 28.6% |
| z | 3 | 10.7% |
| a | 3 | 10.7% |
| c | 2 | 7.1% |
| p | 2 | 7.1% |
| m | 2 | 7.1% |
| x | 2 | 7.1% |
| y | 1 | 3.6% |
+ 5 more answers
Random number 1-10 · English
n = 30 · H = 2.26 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 10 | 33.3% |
| 5 | 8 | 26.7% |
| 8 | 6 | 20.0% |
| 6 | 3 | 10.0% |
| 9 | 2 | 6.7% |
| 4 | 1 | 3.3% |
Random number 1-10 · Chinese
n = 30 · H = 2.47 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 11 | 36.7% |
| 6 | 6 | 20.0% |
| 3 | 5 | 16.7% |
| 5 | 4 | 13.3% |
| 4 | 1 | 3.3% |
| 8 | 1 | 3.3% |
| 9 | 1 | 3.3% |
| 10 | 1 | 3.3% |
Random number 1-100 · English
n = 30 · H = 4.09 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 5 | 16.7% |
| 27 | 3 | 10.0% |
| 37 | 2 | 6.7% |
| 57 | 2 | 6.7% |
| 64 | 2 | 6.7% |
| 73 | 2 | 6.7% |
| 1 | 1 | 3.3% |
| 10 | 1 | 3.3% |
+ 12 more answers
Random number 1-100 · Chinese
n = 30 · H = 3.95 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 47 | 4 | 13.3% |
| 76 | 4 | 13.3% |
| 75 | 3 | 10.0% |
| 42 | 2 | 6.7% |
| 52 | 2 | 6.7% |
| 72 | 2 | 6.7% |
| 87 | 2 | 6.7% |
| 23 | 1 | 3.3% |
+ 10 more answers
Want to verify your API really serves GPT-3.5 Turbo Instruct?
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.