mistralai/mistral-nemo behavioral LLM fingerprint
This page breaks down the exact reference that VerifyLLMAPI uses for mistralai/mistral-nemo: 116 normalized answers across eight low-entropy probes, plus its nearest enrolled models by mean Jensen–Shannon divergence.
Fingerprint summary
- Reference answers
- 116
- Samples per cell
- 13–15
- Nearest model
- mistralai/voxtral-small-24b-2507
- Nearest mean JSD
- 0.555610
The most concentrated cell was word-random|en: apple held 60.0% of its answers and entropy measured 1.472 bits. The broadest cell was letter-random|zh at 3.907 bits.
Against the closest enrolled model, animal-random|ar contributed the largest cell distance at JSD 1.000000. This is a descriptive comparison, not proof that either API route serves a named checkpoint.
Completeness: the author dataset allows up to 15 valid answers per selected cell in reference half A. This model contains 116/120 across the eight cells. We show the actual denominator for every share.
The eight test requests
The research pipeline sent each user prompt with a one-answer system constraint, temperature 1, a 16-token output cap, and reasoning disabled. VerifyLLMAPI uses the same prompt text and normalization target.
| Cell | Task | Exact request text | Normalization and n |
|---|---|---|---|
animal-random|en |
Random animal · English | Name a random animal.System constraintAnswer with a single word or a single number only. Output nothing else: no explanation, no punctuation, no quotation marks. |
word · 15/15 reference samples |
word-random|en |
Random word · English | Name a random word.System constraintAnswer with a single word or a single number only. Output nothing else: no explanation, no punctuation, no quotation marks. |
word · 15/15 reference samples |
animal-random|ru |
Random animal · Russian | Назови случайное животное.System constraintОтвечай только одним словом или одним числом. Не выводи ничего больше: без объяснений, без знаков препинания, без кавычек. |
word · 14/15 reference samples |
animal-random|ar |
Random animal · Arabic | اذكر حيواناً عشوائياً.System constraintأجب بكلمة واحدة أو رقم واحد فقط. لا تكتب أي شيء آخر: لا شرح ولا علامات ترقيم ولا علامات اقتباس. |
word · 15/15 reference samples |
letter-random|zh |
Random character · Chinese | 说出一个随机的汉字。System constraint只用一个词或一个数字回答。不要输出任何其他内容：不要解释，不要标点符号，不要引号。 |
grapheme · 15/15 reference samples |
animal-random|zh |
Random animal · Chinese | 说出一个随机的动物。System constraint只用一个词或一个数字回答。不要输出任何其他内容：不要解释，不要标点符号，不要引号。 |
word · 15/15 reference samples |
letter-random|ar |
Random letter · Arabic | اذكر حرفاً عشوائياً من الحروف الأبجدية.System constraintأجب بكلمة واحدة أو رقم واحد فقط. لا تكتب أي شيء آخر: لا شرح ولا علامات ترقيم ولا علامات اقتباس. |
grapheme · 13/15 reference samples |
color-random|zh |
Random color · Chinese | 说出一个随机的颜色。System constraint只用一个词或一个数字回答。不要输出任何其他内容：不要解释，不要标点符号，不要引号。 |
word · 14/15 reference samples |
Response distributions
These are normalized reference-half counts from the published OpenRouter dataset. The tables contain aggregate values, not user data or a live VerifyLLMAPI scan.
1. animal-random|en
Random animal, English. 15 valid reference answers produced 11 normalized values. The mode was cat at 3/15 (20.0%); entropy was 3.273 bits.
| Normalized response | Count | Share |
|---|---|---|
cat |
3 | 20.0% |
dog |
3 | 20.0% |
bison |
1 | 6.7% |
chick |
1 | 6.7% |
dolphin |
1 | 6.7% |
duck |
1 | 6.7% |
fox |
1 | 6.7% |
ibis |
1 | 6.7% |
lion |
1 | 6.7% |
rat |
1 | 6.7% |
zebra |
1 | 6.7% |
2. word-random|en
Random word, English. 15 valid reference answers produced 4 normalized values. The mode was apple at 9/15 (60.0%); entropy was 1.472 bits.
| Normalized response | Count | Share |
|---|---|---|
apple |
9 | 60.0% |
cat |
4 | 26.7% |
dog |
1 | 6.7% |
lemon |
1 | 6.7% |
3. animal-random|ru
Random animal, Russian. 14 valid reference answers produced 11 normalized values. The mode was собака at 3/14 (21.4%); entropy was 3.325 bits.
| Normalized response | Count | Share |
|---|---|---|
собака |
3 | 21.4% |
лис |
2 | 14.3% |
волк |
1 | 7.1% |
змея |
1 | 7.1% |
кот |
1 | 7.1% |
лев |
1 | 7.1% |
словец |
1 | 7.1% |
слон |
1 | 7.1% |
хищник |
1 | 7.1% |
черепаха |
1 | 7.1% |
칠 |
1 | 7.1% |
4. animal-random|ar
Random animal, Arabic. 15 valid reference answers produced 14 normalized values. The mode was كلب at 2/15 (13.3%); entropy was 3.774 bits.
| Normalized response | Count | Share |
|---|---|---|
كلب |
2 | 13.3% |
bush |
1 | 6.7% |
løve |
1 | 6.7% |
malgré |
1 | 6.7% |
statewide |
1 | 6.7% |
السباع |
1 | 6.7% |
خلد |
1 | 6.7% |
سمك |
1 | 6.7% |
سمكة |
1 | 6.7% |
فennec |
1 | 6.7% |
فهد |
1 | 6.7% |
ق |
1 | 6.7% |
قط |
1 | 6.7% |
ني |
1 | 6.7% |
5. letter-random|zh
Random character, Chinese. 15 valid reference answers produced 15 normalized values. The mode was ajar at 1/15 (6.7%); entropy was 3.907 bits.
| Normalized response | Count | Share |
|---|---|---|
ajar |
1 | 6.7% |
calcular |
1 | 6.7% |
orn |
1 | 6.7% |
компью |
1 | 6.7% |
اگ |
1 | 6.7% |
ానం |
1 | 6.7% |
一 |
1 | 6.7% |
剑 |
1 | 6.7% |
印 |
1 | 6.7% |
地 |
1 | 6.7% |
子 |
1 | 6.7% |
日 |
1 | 6.7% |
梦 |
1 | 6.7% |
的 |
1 | 6.7% |
选 |
1 | 6.7% |
6. animal-random|zh
Random animal, Chinese. 15 valid reference answers produced 12 normalized values. The mode was 狮子 at 2/15 (13.3%); entropy was 3.507 bits.
| Normalized response | Count | Share |
|---|---|---|
狮子 |
2 | 13.3% |
猫 |
2 | 13.3% |
老虎 |
2 | 13.3% |
cat |
1 | 6.7% |
dolphin |
1 | 6.7% |
hedgehog |
1 | 6.7% |
tiger |
1 | 6.7% |
狗 |
1 | 6.7% |
肉虫 |
1 | 6.7% |
蛇 |
1 | 6.7% |
🐶 |
1 | 6.7% |
🦊 |
1 | 6.7% |
7. letter-random|ar
Random letter, Arabic. 13 valid reference answers produced 7 normalized values. The mode was a at 5/13 (38.5%); entropy was 2.442 bits.
| Normalized response | Count | Share |
|---|---|---|
a |
5 | 38.5% |
ج |
3 | 23.1% |
b |
1 | 7.7% |
h |
1 | 7.7% |
أ |
1 | 7.7% |
ا |
1 | 7.7% |
ب |
1 | 7.7% |
8. color-random|zh
Random color, Chinese. 14 valid reference answers produced 11 normalized values. The mode was 绿 at 4/14 (28.6%); entropy was 3.236 bits.
| Normalized response | Count | Share |
|---|---|---|
12 |
1 | 7.1% |
绿 |
4 | 28.6% |
33cc33 |
1 | 7.1% |
blue |
1 | 7.1% |
blues |
1 | 7.1% |
red |
1 | 7.1% |
紫色 |
1 | 7.1% |
红 |
1 | 7.1% |
蓝 |
1 | 7.1% |
蓝色 |
1 | 7.1% |
青 |
1 | 7.1% |
Three nearest enrolled references
We compute base-2 JSD for each of the eight categorical distributions, then average the eight distances. A lower value means more similar answer frequencies within this product reference. It does not identify an unknown route by itself.
| Rank | Reference model | Mean 8-cell JSD |
|---|---|---|
| 1 | mistralai/voxtral-small-24b-2507 |
0.555610 |
| 2 | x-ai/grok-4.3 |
0.597271 |
| 3 | qwen/qwen3.7-plus |
0.617406 |
How many live requests does verification use?
| Profile | Cells × samples | Fresh model requests | Same-data EER |
|---|---|---|---|
| Quick, default complete check | 4 × 5 | 20 | 11.8% |
| Standard | 8 × 5 | 40 | 8.1% |
| Paper budget | 8 × 15 | 120 | 6.7% |
The current-Agent workflow starts with quick. Each answer comes from a fresh Codex or Claude Code process that reuses host-managed login. These requests can consume host allowance or provider balance.
What this fingerprint can and cannot show
- The reference records behavior observed through OpenRouter in the author dataset. Provider wrappers, model updates, decoding, and date can move a distribution.
- The author collection set temperature 1 and disabled reasoning. Current-Agent mode labels sampling as a host default because supported Agent CLIs expose no temperature flag.
- The eight high-gap cells and product thresholds use the same public cohort. Their EER values are calibration results, not an independent production accuracy claim.
- A nearest reference is a similarity result. VerifyLLMAPI returns INCONCLUSIVE when the claimed route lacks an enrolled fingerprint.
Primary sources, license, and reproducibility
- Tomas Bruckner, One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions, arXiv:2607.10252v1.
- Author dataset and derived results, DOI 10.5281/zenodo.21278557, CC BY 4.0.
- Author collection and analysis software, DOI 10.5281/zenodo.21278793, MIT.
- VerifyLLMAPI atlas JSON, built from reference
pamela-openrouter-2026-07-8cell-ref-a, SHA-25651f3f63cbcfb56b151055d2d10e36a9cc2f0644cc68b580784853d68951fa866.
Page evidence SHA-256: 08bb5c4e0fb1dc67ac324245d2687e02e289476f5adaefbc52d35a515da2b195. This hash covers the model ID, eight cell metrics, nearest references, and strongest cell difference in the generated atlas.