Jamba Large 1.7 Behavioral Fingerprint
How AI21's Jamba Large 1.7 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 450 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
AI21
Data generated
2026-07-08
Probe cells
15
Valid samples
450
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)
47
24 / 30 answers
Favorite color
blue
14 / 30 answers
Coin flip: heads
82%
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 = 0.78 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 23 | 76.7% |
| tails | 7 | 23.3% |
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 = 0.00 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
Favorite number · Chinese
n = 30 · H = 0.00 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
Random animal · English
n = 30 · H = 2.79 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| zebra | 10 | 33.3% |
| elephant | 5 | 16.7% |
| giraffe | 4 | 13.3% |
| dog | 3 | 10.0% |
| tiger | 2 | 6.7% |
| dolphin | 2 | 6.7% |
| cat | 2 | 6.7% |
| horse | 1 | 3.3% |
+ 1 more answers
Random animal · Chinese
n = 30 · H = 2.68 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 狮子 | 10 | 33.3% |
| cat | 8 | 26.7% |
| 鸟 | 3 | 10.0% |
| dog | 3 | 10.0% |
| 猫 | 1 | 3.3% |
| elephant | 1 | 3.3% |
| 熊 | 1 | 3.3% |
| panda | 1 | 3.3% |
+ 2 more answers
Random city · English
n = 30 · H = 2.56 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| paris | 11 | 36.7% |
| tokyo | 6 | 20.0% |
| mumbai | 4 | 13.3% |
| berlin | 3 | 10.0% |
| london | 2 | 6.7% |
| istanbul | 2 | 6.7% |
| cairo | 1 | 3.3% |
| moscow | 1 | 3.3% |
Random city · Chinese
n = 30 · H = 2.32 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 上海 | 14 | 46.7% |
| 伦敦 | 6 | 20.0% |
| 巴黎 | 3 | 10.0% |
| 柏林 | 2 | 6.7% |
| 北京 | 2 | 6.7% |
| 威斯康星 | 1 | 3.3% |
| paris | 1 | 3.3% |
| london | 1 | 3.3% |
Random color · English
n = 30 · H = 2.14 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 14 | 46.7% |
| green | 6 | 20.0% |
| red | 3 | 10.0% |
| orange | 3 | 10.0% |
| purple | 3 | 10.0% |
| yellow | 1 | 3.3% |
Random color · Chinese
n = 30 · H = 2.34 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 红 | 9 | 30.0% |
| red | 8 | 26.7% |
| 蓝 | 5 | 16.7% |
| 绿 | 4 | 13.3% |
| blue | 3 | 10.0% |
| green | 1 | 3.3% |
Random letter · English
n = 30 · H = 2.19 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| z | 15 | 50.0% |
| g | 4 | 13.3% |
| f | 4 | 13.3% |
| c | 3 | 10.0% |
| w | 2 | 6.7% |
| u | 1 | 3.3% |
| k | 1 | 3.3% |
Random number 1-10 · English
n = 30 · H = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 30 | 100.0% |
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 = 1.01 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 47 | 24 | 80.0% |
| 42 | 3 | 10.0% |
| 37 | 2 | 6.7% |
| 63 | 1 | 3.3% |
Random number 1-100 · Chinese
n = 30 · H = 1.25 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 47 | 22 | 73.3% |
| 42 | 5 | 16.7% |
| 7 | 1 | 3.3% |
| 23 | 1 | 3.3% |
| 37 | 1 | 3.3% |
Want to verify your API really serves Jamba Large 1.7?
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.