Original research
Name Pair Benchmark
Twenty deliberately varied pairs run through the same deterministic engine used by Ship Name Lab. Inputs, thresholds, top results, and failures are public so changes can be checked instead of trusted.
- Cases
- 20
- Passing
- 20/20
- Engine
- 2026.07.03-3
- Reviewed
- 2026-07-03
What counts as a pass
Each case declares a minimum score and a maximum warning count before the engine runs. A passing result must produce a candidate using material from both inputs, meet that score floor, and stay within the warning limit. The benchmark does not claim that the first result is objectively the best nickname; human taste and pronunciation still decide that.
Common Latin-script cases use stricter thresholds. Diacritic and non-Latin cases intentionally permit one warning because the current readability model does not claim language-specific pronunciation knowledge. That limitation is visible rather than hidden.
Current run
Generated at request time from engine 2026.07.03-3.
| Pair | Category | Top candidate | Score | Warnings | Threshold | Result |
|---|---|---|---|---|---|---|
| Taylor + TravisSimilar opening consonants create several plausible boundaries. | Common Latin | Tayvis | 99 | 0 | ≥82; ≤0 | Pass |
| Alex + JordanTests a short first input against a longer second input. | Common Latin | Aledan | 99 | 0 | ≥82; ≤0 | Pass |
| Sofia + MateoBoth inputs contain open vowel sequences. | Common Latin | Softeo | 97 | 0 | ≥82; ≤0 | Pass |
| Emma + NoahTests two compact, vowel-heavy names. | Common Latin | Emmoah | 99 | 0 | ≥82; ≤0 | Pass |
| Chloe + MasonThe written and spoken boundaries may not agree. | Common Latin | Masloe | 97 | 0 | ≥80; ≤0 | Pass |
| Daniel + OliviaTests two medium-length names with many possible cuts. | Common Latin | Danvia | 97 | 0 | ≥82; ≤0 | Pass |
| Bo + JoTwo-letter inputs leave almost no room for source-preserving cuts. | Short | Bojo | 77 | 0 | ≥75; ≤1 | Pass |
| Ann + LeeTests compact inputs and repeated-letter handling. | Short | Anee | 94 | 0 | ≥78; ≤1 | Pass |
| Kai + AvaBoth names are short and vowel-heavy. | Short | Kava | 94 | 0 | ≥78; ≤1 | Pass |
| Elizabeth + JonathanTests whether the engine avoids simply joining two long names. | Long | Jonabeth | 99 | 0 | ≥82; ≤0 | Pass |
| Christopher + AlexandraA large cut space should still produce compact leaders. | Long | Alexopher | 92 | 0 | ≥82; ≤0 | Pass |
| Aaliyah + MuhammadTests repeated letters and differing source lengths. | Long | Muhyah | 99 | 0 | ≥80; ≤1 | Pass |
| Mary-Jane + O'ConnorSeparators are normalized before candidate construction. | Punctuation | Marnor | 97 | 0 | ≥80; ≤0 | Pass |
| Anne-Marie + Jean-LucTests two compound names after punctuation normalization. | Punctuation | Jeanarie | 97 | 0 | ≥80; ≤0 | Pass |
| Zoë + ChloéLatin diacritics are retained and flagged for human pronunciation review. | Diacritics | Zoloé | 93 | 1 | ≥75; ≤1 | Pass |
| José + MaríaTests source preservation when accented letters are present. | Diacritics | Marosé | 99 | 1 | ≥75; ≤1 | Pass |
| Łukasz + ZofiaThe non-ASCII join requires review by a relevant-language speaker. | Diacritics | Zofasz | 99 | 0 | ≥75; ≤1 | Pass |
| 小明 + 小红Character slicing is deterministic, but pronunciation is not scored. | Non-Latin | 小明小红 | 76 | 1 | ≥65; ≤1 | Pass |
| はるか + れんKana inputs expose the boundary of the Latin readability heuristic. | Non-Latin | はるかれん | 76 | 1 | ≥65; ≤1 | Pass |
| 민준 + 서연Hangul output is generated but explicitly left for human language review. | Non-Latin | 민준서연 | 80 | 1 | ≥65; ≤1 | Pass |
Known limits
The engine scores visible character structure, not cultural meaning, gender, relationship suitability, trademark status, handle availability, or pronunciation in a specific language. Non-Latin results are candidates for human review, not linguistic validation. New engine versions may change rankings; the version and review date above make those changes auditable.