Gemini 3.1 Flash Lite Behavioral Fingerprint
How Google's Gemini 3.1 Flash Lite 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
Data generated
2026-07-08
Probe cells
15
Valid samples
450
Randomness score
20 / 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
26 / 30 answers
Favorite color
blue
26 / 30 answers
Coin flip: heads
90%
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 = 0.72 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 24 | 80.0% |
| tails | 6 | 20.0% |
Coin flip · Chinese
n = 30 · H = 0.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 30 | 100.0% |
Favorite number · English
n = 30 · H = 1.00 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 16 | 53.3% |
| 42 | 14 | 46.7% |
Favorite number · Chinese
n = 30 · H = 0.72 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 24 | 80.0% |
| 42 | 6 | 20.0% |
Random animal · English
n = 30 · H = 2.02 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| elephant | 15 | 50.0% |
| tiger | 8 | 26.7% |
| penguin | 2 | 6.7% |
| giraffe | 2 | 6.7% |
| elephants | 1 | 3.3% |
| wolf | 1 | 3.3% |
| capybara | 1 | 3.3% |
Random animal · Chinese
n = 30 · H = 1.63 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 企鹅 | 21 | 70.0% |
| 老虎 | 2 | 6.7% |
| 猫 | 2 | 6.7% |
| 斑马 | 2 | 6.7% |
| 熊猫 | 1 | 3.3% |
| 豹 | 1 | 3.3% |
| 长颈鹿 | 1 | 3.3% |
Random city · English
n = 30 · H = 0.88 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| tokyo | 21 | 70.0% |
| kyoto | 9 | 30.0% |
Random city · Chinese
n = 30 · H = 2.28 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 成都 | 16 | 53.3% |
| 杭州 | 4 | 13.3% |
| 上海 | 3 | 10.0% |
| 北京 | 2 | 6.7% |
| 重庆 | 1 | 3.3% |
| 巴黎 | 1 | 3.3% |
| 兰州 | 1 | 3.3% |
| 东京 | 1 | 3.3% |
+ 1 more answers
Random color · English
n = 30 · H = 0.70 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 26 | 86.7% |
| azure | 2 | 6.7% |
| indigo | 2 | 6.7% |
Random color · Chinese
n = 30 · H = 2.14 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 青 | 12 | 40.0% |
| 紫 | 10 | 33.3% |
| 蓝 | 3 | 10.0% |
| 靛青 | 2 | 6.7% |
| 翠绿 | 1 | 3.3% |
| 绿 | 1 | 3.3% |
| quoise | 1 | 3.3% |
Random letter · English
n = 30 · H = 1.31 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| k | 21 | 70.0% |
| q | 5 | 16.7% |
| g | 2 | 6.7% |
| m | 2 | 6.7% |
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 = 0.67 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 26 | 86.7% |
| 47 | 3 | 10.0% |
| 74 | 1 | 3.3% |
Random number 1-100 · Chinese
n = 30 · H = 0.21 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 29 | 96.7% |
| 47 | 1 | 3.3% |
Want to verify your API really serves Gemini 3.1 Flash Lite?
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.