Llama 3.2 11B Vision Instruct Behavioral Fingerprint
How Meta's Llama 3.2 11B Vision Instruct answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 425 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
Meta
Data generated
2026-07-08
Probe cells
15
Valid samples
425
Randomness score
59 / 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)
87
6 / 30 answers
Favorite color
turquoise
22 / 30 answers
Coin flip: heads
60%
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 = 29 · H = 0.96 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 18 | 62.1% |
| tails | 11 | 37.9% |
Coin flip · Chinese
n = 28 · H = 0.99 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 16 | 57.1% |
| tails | 12 | 42.9% |
Favorite number · English
n = 12 · H = 3.25 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 5 | 2 | 16.7% |
| 7 | 2 | 16.7% |
| 0 | 1 | 8.3% |
| 2 | 1 | 8.3% |
| 3 | 1 | 8.3% |
| 6 | 1 | 8.3% |
| 13 | 1 | 8.3% |
| 41 | 1 | 8.3% |
+ 2 more answers
Favorite number · Chinese
n = 30 · H = 2.17 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 8 | 14 | 46.7% |
| 7 | 8 | 26.7% |
| 0 | 3 | 10.0% |
| 2 | 1 | 3.3% |
| 3 | 1 | 3.3% |
| 6 | 1 | 3.3% |
| 11 | 1 | 3.3% |
| 777 | 1 | 3.3% |
Random animal · English
n = 30 · H = 2.82 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| koala | 11 | 36.7% |
| kangaroo | 7 | 23.3% |
| giraffe | 3 | 10.0% |
| rabbit | 1 | 3.3% |
| hedgehog | 1 | 3.3% |
| leopard | 1 | 3.3% |
| ostrich | 1 | 3.3% |
| flamingo | 1 | 3.3% |
+ 4 more answers
Random animal · Chinese
n = 29 · H = 4.14 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 河马 | 4 | 13.8% |
| 企鹅 | 3 | 10.3% |
| 松鼠 | 2 | 6.9% |
| 大象 | 2 | 6.9% |
| 驴 | 2 | 6.9% |
| 狮子 | 2 | 6.9% |
| endorsement | 1 | 3.4% |
| 黄雀 | 1 | 3.4% |
+ 12 more answers
Random city · English
n = 30 · H = 4.64 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| reno | 2 | 6.7% |
| zurich | 2 | 6.7% |
| birmingham | 2 | 6.7% |
| lisbon | 2 | 6.7% |
| edmonton | 1 | 3.3% |
| tashkent | 1 | 3.3% |
| turin | 1 | 3.3% |
| munich | 1 | 3.3% |
+ 18 more answers
Random city · Chinese
n = 29 · H = 4.65 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 曼彻斯特 | 2 | 6.9% |
| 悉尼 | 2 | 6.9% |
| 卡尔加里 | 2 | 6.9% |
| 西雅图 | 1 | 3.4% |
| 多伦多 | 1 | 3.4% |
| 利马 | 1 | 3.4% |
| defaultcenter | 1 | 3.4% |
| 深圳 | 1 | 3.4% |
+ 18 more answers
Random color · English
n = 30 · H = 1.41 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| turquoise | 22 | 73.3% |
| purple | 3 | 10.0% |
| mauve | 2 | 6.7% |
| indigo | 1 | 3.3% |
| magenta | 1 | 3.3% |
| blue | 1 | 3.3% |
Random color · Chinese
n = 29 · H = 2.79 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 紫 | 13 | 44.8% |
| 橙 | 4 | 13.8% |
| 蓝 | 2 | 6.9% |
| 绿 | 2 | 6.9% |
| 灰 | 1 | 3.4% |
| 苹果红 | 1 | 3.4% |
| 皇 | 1 | 3.4% |
| 白 | 1 | 3.4% |
+ 4 more answers
Random letter · English
n = 30 · H = 2.27 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| k | 15 | 50.0% |
| q | 5 | 16.7% |
| n | 3 | 10.0% |
| j | 2 | 6.7% |
| o | 2 | 6.7% |
| l | 1 | 3.3% |
| x | 1 | 3.3% |
| w | 1 | 3.3% |
Random number 1-10 · English
n = 30 · H = 1.01 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 24 | 80.0% |
| 8 | 3 | 10.0% |
| 5 | 2 | 6.7% |
| 9 | 1 | 3.3% |
Random number 1-10 · Chinese
n = 29 · H = 2.43 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 8 | 10 | 34.5% |
| 7 | 6 | 20.7% |
| 3 | 5 | 17.2% |
| 6 | 4 | 13.8% |
| 5 | 2 | 6.9% |
| 4 | 1 | 3.4% |
| 9 | 1 | 3.4% |
Random number 1-100 · English
n = 30 · H = 3.61 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 87 | 6 | 20.0% |
| 53 | 4 | 13.3% |
| 43 | 3 | 10.0% |
| 85 | 3 | 10.0% |
| 14 | 2 | 6.7% |
| 42 | 2 | 6.7% |
| 74 | 2 | 6.7% |
| 34 | 1 | 3.3% |
+ 7 more answers
Random number 1-100 · Chinese
n = 30 · H = 4.42 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 13 | 3 | 10.0% |
| 34 | 2 | 6.7% |
| 42 | 2 | 6.7% |
| 67 | 2 | 6.7% |
| 82 | 2 | 6.7% |
| 83 | 2 | 6.7% |
| 32 | 1 | 3.3% |
| 33 | 1 | 3.3% |
+ 15 more answers
Want to verify your API really serves Llama 3.2 11B Vision 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.