Kimi K2.6 Behavioral Fingerprint

How MoonshotAI's Kimi K2.6 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 434 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

MoonshotAI

Data generated

2026-07-08

Probe cells

15

Valid samples

434

Randomness score

32 / 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)

37

12 / 30 answers

Favorite color

magenta

9 / 27 answers

Coin flip: heads

93%

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 = 0.21 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2996.7%
tails13.3%

Coin flip · Chinese

n = 30 · H = 0.47 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2790.0%
tails310.0%

Favorite number · English

n = 29 · H = 1.14 bit · uniform baseline 13.29 bit

AnswerCountShare
72172.4%
42620.7%
413.4%
813.4%

Favorite number · Chinese

n = 29 · H = 0.36 bit · uniform baseline 13.29 bit

AnswerCountShare
72793.1%
4226.9%

Random animal · English

n = 29 · H = 2.61 bit · uniform baseline 5.64 bit

AnswerCountShare
platypus931.0%
axolotl827.6%
octopus413.8%
aardvark310.3%
elephant13.4%
ocelot13.4%
giraffe13.4%
jaguar13.4%

+ 1 more answers

Random animal · Chinese

n = 30 · H = 3.76 bit · uniform baseline 5.64 bit

AnswerCountShare
长颈鹿723.3%
老虎310.0%
26.7%
26.7%
穿山甲26.7%
狮子26.7%
狐狸26.7%
海豚13.3%

+ 9 more answers

Random city · English

n = 25 · H = 3.26 bit · uniform baseline 5.64 bit

AnswerCountShare
bishkek936.0%
lviv28.0%
tashkent28.0%
vilnius28.0%
nairobi14.0%
osaka14.0%
portland14.0%
brest14.0%

+ 6 more answers

Random city · Chinese

n = 30 · H = 2.30 bit · uniform baseline 5.64 bit

AnswerCountShare
成都1136.7%
杭州930.0%
上海516.7%
乌兰巴托13.3%
天津13.3%
哥本哈根13.3%
巴塞罗那13.3%
武汉13.3%

Random color · English

n = 27 · H = 2.84 bit · uniform baseline 4.91 bit

AnswerCountShare
magenta933.3%
teal518.5%
azure311.1%
cyan311.1%
crimson27.4%
purple13.7%
aquamarine13.7%
cerulean13.7%

+ 2 more answers

Random color · Chinese

n = 30 · H = 1.83 bit · uniform baseline 4.91 bit

AnswerCountShare
靛蓝2066.7%
26.7%
26.7%
靛青26.7%
靛蓝紫13.3%
13.3%
13.3%
青碧13.3%

Random letter · English

n = 28 · H = 2.01 bit · uniform baseline 4.70 bit

AnswerCountShare
q1450.0%
k621.4%
m310.7%
x310.7%
w13.6%
y13.6%

Random number 1-10 · English

n = 29 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
729100.0%

Random number 1-10 · Chinese

n = 29 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
729100.0%

Random number 1-100 · English

n = 30 · H = 1.78 bit · uniform baseline 6.64 bit

AnswerCountShare
371240.0%
471033.3%
73620.0%
4226.7%

Random number 1-100 · Chinese

n = 29 · H = 1.82 bit · uniform baseline 6.64 bit

AnswerCountShare
731655.2%
37413.8%
42413.8%
47413.8%
713.4%

Want to verify your API really serves Kimi K2.6?

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 endpoint

Data 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.

Paper on arXivDataset on ZenodoCC-BY-4.0 license

More MoonshotAI model fingerprints

Browse all 167 model fingerprints

Kimi K2.6 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai