Claude Haiku 4.5 Behavioral Fingerprint

How Anthropic's Claude Haiku 4.5 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 420 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Anthropic

Data generated

2026-07-08

Probe cells

14

Valid samples

420

Randomness score

18 / 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

25 / 30 answers

Favorite color

blue

20 / 30 answers

Coin flip: heads

100%

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 = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads30100.0%

Coin flip · Chinese

n = 30 · H = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads30100.0%

Favorite number · Chinese

n = 30 · H = 1.05 bit · uniform baseline 13.29 bit

AnswerCountShare
72273.3%
42620.0%
326.7%

Random animal · English

n = 30 · H = 2.20 bit · uniform baseline 5.64 bit

AnswerCountShare
giraffe1136.7%
platypus1033.3%
otter413.3%
penguin26.7%
llama13.3%
flamingo13.3%
elephant13.3%

Random animal · Chinese

n = 30 · H = 2.42 bit · uniform baseline 5.64 bit

AnswerCountShare
熊猫1033.3%
长颈鹿723.3%
狐狸516.7%
猫鼬413.3%
26.7%
企鹅13.3%
斑马13.3%

Random city · English

n = 30 · H = 2.37 bit · uniform baseline 5.64 bit

AnswerCountShare
denver1446.7%
tokyo413.3%
portland413.3%
paris310.0%
barcelona26.7%
kyoto13.3%
seattle13.3%
lisbon13.3%

Random city · Chinese

n = 30 · H = 1.93 bit · uniform baseline 5.64 bit

AnswerCountShare
杭州1653.3%
成都516.7%
西安516.7%
苏州26.7%
温州13.3%
重庆13.3%

Random color · English

n = 30 · H = 1.55 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2066.7%
azure310.0%
purple310.0%
turquoise310.0%
teal13.3%

Random color · Chinese

n = 30 · H = 0.42 bit · uniform baseline 4.91 bit

AnswerCountShare
2893.3%
绿13.3%
13.3%

Random letter · English

n = 30 · H = 1.01 bit · uniform baseline 4.70 bit

AnswerCountShare
q2376.7%
k413.3%
g310.0%

Random number 1-10 · English

n = 30 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-10 · Chinese

n = 30 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-100 · English

n = 30 · H = 0.65 bit · uniform baseline 6.64 bit

AnswerCountShare
422583.3%
47516.7%

Random number 1-100 · Chinese

n = 30 · H = 0.65 bit · uniform baseline 6.64 bit

AnswerCountShare
422583.3%
47516.7%

Want to verify your API really serves Claude Haiku 4.5?

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 Anthropic model fingerprints

Browse all 167 model fingerprints

Claude Haiku 4.5 Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai