Qwen3 30B A3B Instruct 2507 Behavioral Fingerprint
How Qwen's Qwen3 30B A3B Instruct 2507 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 439 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
Qwen
Data generated
2026-07-08
Probe cells
15
Valid samples
439
Randomness score
19 / 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
30 / 30 answers
Favorite color
blue
29 / 30 answers
Coin flip: heads
86%
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 = 0.85 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 21 | 72.4% |
| tails | 8 | 27.6% |
Coin flip · Chinese
n = 29 · H = 0.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 29 | 100.0% |
Favorite number · English
n = 28 · H = 0.00 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 28 | 100.0% |
Favorite number · Chinese
n = 29 · H = 0.00 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 29 | 100.0% |
Random animal · English
n = 29 · H = 1.73 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| lion | 17 | 58.6% |
| elephant | 5 | 17.2% |
| tiger | 3 | 10.3% |
| dog | 3 | 10.3% |
| penguin | 1 | 3.4% |
Random animal · Chinese
n = 30 · H = 1.78 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 老虎 | 17 | 56.7% |
| 狮子 | 7 | 23.3% |
| 猫 | 3 | 10.0% |
| tiger | 1 | 3.3% |
| 熊猫 | 1 | 3.3% |
| 豹 | 1 | 3.3% |
Random city · English
n = 30 · H = 2.32 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| paris | 14 | 46.7% |
| sydney | 7 | 23.3% |
| tokyo | 3 | 10.0% |
| chicago | 1 | 3.3% |
| melbourne | 1 | 3.3% |
| london | 1 | 3.3% |
| amsterdam | 1 | 3.3% |
| lisbon | 1 | 3.3% |
+ 1 more answers
Random city · Chinese
n = 29 · H = 1.90 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 上海 | 14 | 48.3% |
| 巴黎 | 9 | 31.0% |
| 北京 | 2 | 6.9% |
| 纽约 | 2 | 6.9% |
| 柏林 | 1 | 3.4% |
| 杭州 | 1 | 3.4% |
Random color · English
n = 30 · H = 0.21 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 29 | 96.7% |
| green | 1 | 3.3% |
Random color · Chinese
n = 29 · H = 0.36 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 27 | 93.1% |
| 绿 | 2 | 6.9% |
Random letter · English
n = 30 · H = 2.05 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| m | 18 | 60.0% |
| k | 3 | 10.0% |
| a | 2 | 6.7% |
| b | 2 | 6.7% |
| g | 2 | 6.7% |
| d | 1 | 3.3% |
| e | 1 | 3.3% |
| c | 1 | 3.3% |
Random number 1-10 · English
n = 29 · H = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 29 | 100.0% |
Random number 1-10 · Chinese
n = 28 · H = 0.00 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 28 | 100.0% |
Random number 1-100 · English
n = 30 · H = 0.00 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 30 | 100.0% |
Random number 1-100 · Chinese
n = 30 · H = 0.21 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 29 | 96.7% |
| 67 | 1 | 3.3% |
Want to verify your API really serves Qwen3 30B A3B Instruct 2507?
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.