Hermes 4 70B Behavioral Fingerprint

How Nous's Hermes 4 70B answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 439 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Nous

Data generated

2026-07-08

Probe cells

15

Valid samples

439

Randomness score

47 / 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

6 / 30 answers

Favorite color

cyan

8 / 29 answers

Coin flip: heads

79%

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 = 0.35 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2893.3%
tails26.7%

Coin flip · Chinese

n = 27 · H = 0.95 bit · uniform baseline 1.00 bit

AnswerCountShare
heads1763.0%
tails1037.0%

Favorite number · English

n = 29 · H = 1.48 bit · uniform baseline 13.29 bit

AnswerCountShare
421758.6%
7931.0%
1313.4%
1713.4%
1813.4%

Favorite number · Chinese

n = 30 · H = 0.77 bit · uniform baseline 13.29 bit

AnswerCountShare
72583.3%
42413.3%
513.3%

Random animal · English

n = 29 · H = 3.76 bit · uniform baseline 5.64 bit

AnswerCountShare
kangaroo620.7%
zebra310.3%
lion310.3%
elephant310.3%
giraffe26.9%
tiger13.4%
hippopotamus13.4%
eel13.4%

+ 9 more answers

Random animal · Chinese

n = 26 · H = 3.13 bit · uniform baseline 5.64 bit

AnswerCountShare
830.8%
大象415.4%
狮子311.5%
老虎27.7%
27.7%
蜂猴13.8%
13.8%
13.8%

+ 4 more answers

Random city · English

n = 29 · H = 3.72 bit · uniform baseline 5.64 bit

AnswerCountShare
paris517.2%
zurich413.8%
tokyo310.3%
london310.3%
toronto26.9%
madrid26.9%
chicago13.4%
othello13.4%

+ 8 more answers

Random city · Chinese

n = 30 · H = 2.89 bit · uniform baseline 5.64 bit

AnswerCountShare
大阪1240.0%
北京310.0%
上海310.0%
巴黎26.7%
东京26.7%
悉尼26.7%
伦敦26.7%
新加坡13.3%

+ 3 more answers

Random color · English

n = 29 · H = 3.01 bit · uniform baseline 4.91 bit

AnswerCountShare
cyan827.6%
teal413.8%
green413.8%
blue310.3%
azure310.3%
purple26.9%
chartreuse26.9%
violet13.4%

+ 2 more answers

Random color · Chinese

n = 30 · H = 1.63 bit · uniform baseline 4.91 bit

AnswerCountShare
1756.7%
绿826.7%
310.0%
13.3%
13.3%

Random letter · English

n = 30 · H = 3.34 bit · uniform baseline 4.70 bit

AnswerCountShare
k826.7%
q516.7%
m310.0%
z310.0%
l26.7%
g13.3%
b13.3%
w13.3%

+ 6 more answers

Random number 1-10 · English

n = 30 · H = 1.01 bit · uniform baseline 3.32 bit

AnswerCountShare
72480.0%
5310.0%
826.7%
613.3%

Random number 1-10 · Chinese

n = 30 · H = 0.90 bit · uniform baseline 3.32 bit

AnswerCountShare
72583.3%
326.7%
626.7%
513.3%

Random number 1-100 · English

n = 30 · H = 3.56 bit · uniform baseline 6.64 bit

AnswerCountShare
47620.0%
42413.3%
73413.3%
37310.0%
5826.7%
7426.7%
4313.3%
5913.3%

+ 7 more answers

Random number 1-100 · Chinese

n = 30 · H = 2.87 bit · uniform baseline 6.64 bit

AnswerCountShare
581033.3%
42826.7%
3826.7%
8726.7%
2313.3%
3413.3%
3713.3%
6413.3%

+ 4 more answers

Want to verify your API really serves Hermes 4 70B?

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 Nous model fingerprints

Browse all 167 model fingerprints

Hermes 4 70B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai