Mistral Small 3 Behavioral Fingerprint
How Mistral's Mistral Small 3 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 449 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
Mistral
Data generated
2026-07-08
Probe cells
15
Valid samples
449
Randomness score
55 / 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
14 / 30 answers
Favorite color
blue
22 / 30 answers
Coin flip: heads
47%
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 = 0.97 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| tails | 18 | 60.0% |
| heads | 12 | 40.0% |
Coin flip · Chinese
n = 30 · H = 1.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 16 | 53.3% |
| tails | 14 | 46.7% |
Favorite number · English
n = 29 · H = 1.07 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 22 | 75.9% |
| 7 | 5 | 17.2% |
| 2 | 1 | 3.4% |
| 3 | 1 | 3.4% |
Favorite number · Chinese
n = 30 · H = 2.56 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 10 | 33.3% |
| 7 | 9 | 30.0% |
| 8 | 3 | 10.0% |
| 3 | 2 | 6.7% |
| 6 | 2 | 6.7% |
| 1 | 1 | 3.3% |
| 2 | 1 | 3.3% |
| 5 | 1 | 3.3% |
+ 1 more answers
Random animal · English
n = 30 · H = 4.03 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| squirrel | 7 | 23.3% |
| koala | 3 | 10.0% |
| elephant | 2 | 6.7% |
| pug | 1 | 3.3% |
| spider | 1 | 3.3% |
| cat | 1 | 3.3% |
| ostrich | 1 | 3.3% |
| eagle | 1 | 3.3% |
+ 13 more answers
Random animal · Chinese
n = 30 · H = 3.91 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 狮子 | 8 | 26.7% |
| 狗 | 2 | 6.7% |
| 海豚 | 2 | 6.7% |
| 熊 | 2 | 6.7% |
| 蓝鲸 | 1 | 3.3% |
| 鸟 | 1 | 3.3% |
| 象 | 1 | 3.3% |
| 鸭子 | 1 | 3.3% |
+ 12 more answers
Random city · English
n = 30 · H = 3.92 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| tokyo | 7 | 23.3% |
| paris | 2 | 6.7% |
| london | 2 | 6.7% |
| berlin | 2 | 6.7% |
| oslo | 2 | 6.7% |
| sydney | 2 | 6.7% |
| cancun | 1 | 3.3% |
| toledo | 1 | 3.3% |
+ 11 more answers
Random city · Chinese
n = 30 · H = 3.46 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 东京 | 8 | 26.7% |
| 上海 | 3 | 10.0% |
| 北京 | 3 | 10.0% |
| 西安 | 2 | 6.7% |
| 巴黎 | 2 | 6.7% |
| 柏林 | 2 | 6.7% |
| 杭州 | 2 | 6.7% |
| 苏州 | 2 | 6.7% |
+ 6 more answers
Random color · English
n = 30 · H = 1.25 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 22 | 73.3% |
| green | 5 | 16.7% |
| red | 1 | 3.3% |
| pink | 1 | 3.3% |
| violet | 1 | 3.3% |
Random color · Chinese
n = 30 · H = 2.28 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 16 | 53.3% |
| 绿 | 4 | 13.3% |
| 红 | 3 | 10.0% |
| 紫 | 2 | 6.7% |
| 烟灰 | 1 | 3.3% |
| 黄 | 1 | 3.3% |
| 瑰红 | 1 | 3.3% |
| 浅绿 | 1 | 3.3% |
+ 1 more answers
Random letter · English
n = 30 · H = 3.41 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| k | 5 | 16.7% |
| x | 5 | 16.7% |
| g | 5 | 16.7% |
| b | 2 | 6.7% |
| q | 2 | 6.7% |
| v | 2 | 6.7% |
| m | 2 | 6.7% |
| f | 2 | 6.7% |
+ 5 more answers
Random number 1-10 · English
n = 30 · H = 1.08 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 24 | 80.0% |
| 5 | 3 | 10.0% |
| 3 | 1 | 3.3% |
| 4 | 1 | 3.3% |
| 6 | 1 | 3.3% |
Random number 1-10 · Chinese
n = 30 · H = 2.52 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 10 | 33.3% |
| 3 | 7 | 23.3% |
| 5 | 4 | 13.3% |
| 4 | 3 | 10.0% |
| 2 | 2 | 6.7% |
| 6 | 2 | 6.7% |
| 9 | 2 | 6.7% |
Random number 1-100 · English
n = 30 · H = 1.76 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 47 | 14 | 46.7% |
| 42 | 10 | 33.3% |
| 72 | 4 | 13.3% |
| 40 | 1 | 3.3% |
| 74 | 1 | 3.3% |
Random number 1-100 · Chinese
n = 30 · H = 2.85 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 13 | 43.3% |
| 37 | 3 | 10.0% |
| 47 | 3 | 10.0% |
| 45 | 2 | 6.7% |
| 72 | 2 | 6.7% |
| 23 | 1 | 3.3% |
| 27 | 1 | 3.3% |
| 57 | 1 | 3.3% |
+ 4 more answers
Want to verify your API really serves Mistral Small 3?
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.