Hermes 3 70B Instruct Behavioral Fingerprint
How Nous's Hermes 3 70B Instruct answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 392 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
392
Randomness score
33 / 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
17 / 30 answers
Favorite color
blue
13 / 15 answers
Coin flip: heads
83%
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 = 0.74 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 23 | 79.3% |
| tails | 6 | 20.7% |
Coin flip · Chinese
n = 30 · H = 0.57 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 26 | 86.7% |
| tails | 4 | 13.3% |
Favorite number · English
n = 30 · H = 1.35 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 15 | 50.0% |
| 7 | 13 | 43.3% |
| 3 | 1 | 3.3% |
| 44 | 1 | 3.3% |
Favorite number · Chinese
n = 30 · H = 1.34 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 16 | 53.3% |
| 42 | 12 | 40.0% |
| 5 | 1 | 3.3% |
| 9 | 1 | 3.3% |
Random animal · English
n = 17 · H = 2.13 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| kangaroo | 9 | 52.9% |
| giraffe | 3 | 17.6% |
| raccoon | 1 | 5.9% |
| elephant | 1 | 5.9% |
| koala | 1 | 5.9% |
| zebra | 1 | 5.9% |
| sloth | 1 | 5.9% |
Random animal · Chinese
n = 24 · H = 3.61 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 企鹅 | 6 | 25.0% |
| 海马 | 2 | 8.3% |
| 狮子 | 2 | 8.3% |
| 猴子 | 2 | 8.3% |
| 孔雀 | 2 | 8.3% |
| 大熊猫 | 1 | 4.2% |
| 袋鼠 | 1 | 4.2% |
| 乌龟 | 1 | 4.2% |
+ 7 more answers
Random city · English
n = 11 · H = 2.91 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| chicago | 2 | 18.2% |
| paris | 2 | 18.2% |
| tokyo | 2 | 18.2% |
| seattle | 1 | 9.1% |
| raleigh | 1 | 9.1% |
| madrid | 1 | 9.1% |
| baghdad | 1 | 9.1% |
| stockholm | 1 | 9.1% |
Random city · Chinese
n = 26 · H = 2.44 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 北京 | 13 | 50.0% |
| 悉尼 | 3 | 11.5% |
| 布达佩斯 | 2 | 7.7% |
| 上海 | 2 | 7.7% |
| 东京 | 2 | 7.7% |
| 巴黎 | 1 | 3.8% |
| 张家口 | 1 | 3.8% |
| 孟买 | 1 | 3.8% |
+ 1 more answers
Random color · English
n = 15 · H = 0.70 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 13 | 86.7% |
| indigo | 1 | 6.7% |
| azure | 1 | 6.7% |
Random color · Chinese
n = 30 · H = 0.78 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 23 | 76.7% |
| 绿 | 7 | 23.3% |
Random letter · English
n = 30 · H = 2.19 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| k | 10 | 33.3% |
| f | 8 | 26.7% |
| q | 7 | 23.3% |
| t | 3 | 10.0% |
| x | 1 | 3.3% |
| a | 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% |
| 4 | 3 | 10.0% |
| 3 | 2 | 6.7% |
| 8 | 1 | 3.3% |
Random number 1-10 · Chinese
n = 30 · H = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
Random number 1-100 · English
n = 30 · H = 1.80 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 17 | 56.7% |
| 73 | 7 | 23.3% |
| 58 | 2 | 6.7% |
| 59 | 2 | 6.7% |
| 47 | 1 | 3.3% |
| 75 | 1 | 3.3% |
Random number 1-100 · Chinese
n = 30 · H = 1.41 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 22 | 73.3% |
| 58 | 3 | 10.0% |
| 73 | 2 | 6.7% |
| 57 | 1 | 3.3% |
| 75 | 1 | 3.3% |
| 83 | 1 | 3.3% |
Want to verify your API really serves Hermes 3 70B 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.