cohere/command-r-plus-08-2024 behavioral LLM fingerprint
This page breaks down the exact reference that VerifyLLMAPI uses for cohere/command-r-plus-08-2024: 120 normalized answers across eight low-entropy probes, plus its nearest enrolled models by mean Jensen–Shannon divergence.
Fingerprint summary
- Reference answers
- 120
- Samples per cell
- 15–15
- Nearest model
- x-ai/grok-4.3
- Nearest mean JSD
- 0.748101
The most concentrated cell was color-random|zh: 绿色 held 40.0% of its answers and entropy measured 2.340 bits. The broadest cell was word-random|en at 3.907 bits.
Against the closest enrolled model, letter-random|zh contributed the largest cell distance at JSD 0.908170. 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 120/120 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 · 15/15 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 · 15/15 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 · 15/15 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 13 normalized values. The mode was elephant at 2/15 (13.3%); entropy was 3.640 bits.
| Normalized response | Count | Share |
|---|---|---|
elephant |
2 | 13.3% |
fox |
2 | 13.3% |
aardvark |
1 | 6.7% |
dog |
1 | 6.7% |
koala |
1 | 6.7% |
okapi |
1 | 6.7% |
ostrich |
1 | 6.7% |
owl |
1 | 6.7% |
penguin |
1 | 6.7% |
sheep |
1 | 6.7% |
tiger |
1 | 6.7% |
wombat |
1 | 6.7% |
zebra |
1 | 6.7% |
2. word-random|en
Random word, English. 15 valid reference answers produced 15 normalized values. The mode was apple at 1/15 (6.7%); entropy was 3.907 bits.
| Normalized response | Count | Share |
|---|---|---|
apple |
1 | 6.7% |
articulate |
1 | 6.7% |
cacophony |
1 | 6.7% |
ennui |
1 | 6.7% |
ethereal |
1 | 6.7% |
fusilli |
1 | 6.7% |
galvanize |
1 | 6.7% |
goblin |
1 | 6.7% |
hedgehog |
1 | 6.7% |
hello |
1 | 6.7% |
persimmon |
1 | 6.7% |
plaintiff |
1 | 6.7% |
sunburn |
1 | 6.7% |
supercalifragilisticexpialidocious |
1 | 6.7% |
word |
1 | 6.7% |
3. animal-random|ru
Random animal, Russian. 15 valid reference answers produced 14 normalized values. The mode was медведь at 2/15 (13.3%); entropy was 3.774 bits.
| Normalized response | Count | Share |
|---|---|---|
медведь |
2 | 13.3% |
аист |
1 | 6.7% |
гиена |
1 | 6.7% |
жираф |
1 | 6.7% |
зебра |
1 | 6.7% |
какаду |
1 | 6.7% |
кенгуру |
1 | 6.7% |
лев |
1 | 6.7% |
овца |
1 | 6.7% |
панда |
1 | 6.7% |
слон |
1 | 6.7% |
совёнок |
1 | 6.7% |
хомяк |
1 | 6.7% |
хорёк |
1 | 6.7% |
4. animal-random|ar
Random animal, Arabic. 15 valid reference answers produced 11 normalized values. The mode was البطريق at 2/15 (13.3%); entropy was 3.374 bits.
| Normalized response | Count | Share |
|---|---|---|
البطريق |
2 | 13.3% |
البقرة |
2 | 13.3% |
التمساح |
2 | 13.3% |
الفيل |
2 | 13.3% |
الأسد |
1 | 6.7% |
الحمار |
1 | 6.7% |
الحوت |
1 | 6.7% |
الدلفين |
1 | 6.7% |
الزرافة |
1 | 6.7% |
القط |
1 | 6.7% |
الليمور |
1 | 6.7% |
5. letter-random|zh
Random character, Chinese. 15 valid reference answers produced 14 normalized values. The mode was 信 at 2/15 (13.3%); entropy was 3.774 bits.
| Normalized response | Count | Share |
|---|---|---|
信 |
2 | 13.3% |
丁 |
1 | 6.7% |
丙 |
1 | 6.7% |
令 |
1 | 6.7% |
但 |
1 | 6.7% |
好 |
1 | 6.7% |
安 |
1 | 6.7% |
杏 |
1 | 6.7% |
栀 |
1 | 6.7% |
橡 |
1 | 6.7% |
氧 |
1 | 6.7% |
爱 |
1 | 6.7% |
禾 |
1 | 6.7% |
龙 |
1 | 6.7% |
6. animal-random|zh
Random animal, Chinese. 15 valid reference answers produced 13 normalized values. The mode was 熊猫 at 2/15 (13.3%); entropy was 3.640 bits.
| Normalized response | Count | Share |
|---|---|---|
熊猫 |
2 | 13.3% |
猫 |
2 | 13.3% |
兔子 |
1 | 6.7% |
斑马 |
1 | 6.7% |
河马 |
1 | 6.7% |
狗 |
1 | 6.7% |
狼 |
1 | 6.7% |
猫头鹰 |
1 | 6.7% |
猴子 |
1 | 6.7% |
虎 |
1 | 6.7% |
长颈鹿 |
1 | 6.7% |
鸟 |
1 | 6.7% |
鸵鸟 |
1 | 6.7% |
7. letter-random|ar
Random letter, Arabic. 15 valid reference answers produced 11 normalized values. The mode was ر at 2/15 (13.3%); entropy was 3.374 bits.
| Normalized response | Count | Share |
|---|---|---|
ر |
2 | 13.3% |
ط |
2 | 13.3% |
ق |
2 | 13.3% |
ك |
2 | 13.3% |
أ |
1 | 6.7% |
ا |
1 | 6.7% |
ث |
1 | 6.7% |
ح |
1 | 6.7% |
ص |
1 | 6.7% |
م |
1 | 6.7% |
ﺽ |
1 | 6.7% |
8. color-random|zh
Random color, Chinese. 15 valid reference answers produced 7 normalized values. The mode was 绿色 at 6/15 (40.0%); entropy was 2.340 bits.
| Normalized response | Count | Share |
|---|---|---|
绿色 |
6 | 40.0% |
紫色 |
4 | 26.7% |
白 |
1 | 6.7% |
白色 |
1 | 6.7% |
粉色 |
1 | 6.7% |
青草绿 |
1 | 6.7% |
黑色 |
1 | 6.7% |
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 | x-ai/grok-4.3 |
0.748101 |
| 2 | mistralai/mistral-small-2603 |
0.753777 |
| 3 | meta-llama/llama-3.1-70b-instruct |
0.771705 |
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: 61e59165a1f12ceb9110621f808ee06f7bf043cfe638c48a4211aa678bef5129. This hash covers the model ID, eight cell metrics, nearest references, and strongest cell difference in the generated atlas.