MiMo-V2.5 Behavioral Fingerprint

How Xiaomi's MiMo-V2.5 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 32 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Xiaomi

Data generated

2026-07-08

Probe cells

3

Valid samples

32

Randomness score

43 / 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)

Not covered

Favorite color

teal

4 / 12 answers

Coin flip: heads

Not covered

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.

Random city · Chinese

n = 10 · H = 1.96 bit · uniform baseline 5.64 bit

AnswerCountShare
北京550.0%
东京220.0%
柏林110.0%
芝加哥110.0%
上海110.0%

Random color · English

n = 12 · H = 2.52 bit · uniform baseline 4.91 bit

AnswerCountShare
teal433.3%
coral325.0%
crimson18.3%
turquoise18.3%
magenta18.3%
blue18.3%
red18.3%

Random letter · English

n = 10 · H = 1.97 bit · uniform baseline 4.70 bit

AnswerCountShare
k330.0%
q330.0%
x220.0%
g220.0%

Want to verify your API really serves MiMo-V2.5?

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 Xiaomi model fingerprints

Browse all 167 model fingerprints

MiMo-V2.5 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai