AI Desk · Model Identity · Compare
Ling-3.0-flash · Poolside: Laguna XS 2.1
Identity similarity: lowDivergent fingerprints · 23/50These models tokenise differently. Divergence on the high-information strings (CJK, emoji, digits) separates unrelated vocabularies within a handful of samples.
Ling-3.0-flash recordPoolside: Laguna XS 2.1 recordOpen in the interactive bench
Tokenizer fingerprint
23 of 50 mutually clean strings agree| Test string | Ling-3.0-flash | Poolside: Laguna XS 2.1 | Verdict |
|---|---|---|---|
| en-prose | 14 | 14 | match |
| en-long | 16 | 17 | differs |
| spaces-20 | 3 | 3 | match |
| spaces-60 | 3 | 3 | match |
| tabs-20 | 5 | 3 | differs |
| newlines-20 | 22 | 4 | differs |
| mixed-ws | 9 | 7 | differs |
| digits-9 | 9 | 9 | match |
| digits-12 | 12 | 12 | match |
| digits-30 | 30 | 30 | match |
| digits-sep | 12 | 12 | match |
| float-long | 22 | 22 | match |
| zh-common | 9 | 12 | differs |
| zh-long | 10 | 20 | differs |
| zh-rare | 18 | 20 | differs |
| ja-kana | 10 | 14 | differs |
| ja-kanji | 13 | 15 | differs |
| ko | 12 | 13 | differs |
| ru | 15 | 15 | match |
| ar | 14 | 23 | differs |
| he | 19 | 22 | differs |
| hi | 25 | 26 | differs |
| th | 15 | 25 | differs |
| el | 21 | 24 | differs |
| emoji-basic | 10 | 10 | match |
| emoji-skin | 20 | 20 | match |
| emoji-zwj-family | 11 | 11 | match |
| emoji-zwj-x3 | 33 | 33 | match |
| emoji-flags | 16 | 10 | differs |
| emoji-prof | 20 | 20 | match |
| math | 28 | 24 | differs |
| boxdraw | 30 | 27 | differs |
| combining | 5 | 12 | differs |
| cjk-ext-b | 16 | 16 | match |
| surrogates | 40 | 37 | differs |
| zalgo | 36 | 36 | match |
| rtl-mix | 9 | 11 | differs |
| py-code | 26 | 26 | match |
| py-indent | 18 | 18 | match |
| json | 25 | 25 | match |
| html | 16 | 16 | match |
| regex | 45 | 42 | differs |
| camel | 5 | 6 | differs |
| snake | 6 | 6 | match |
| rare-word-x5 | 31 | 36 | differs |
| repeat-tok | 41 | 22 | differs |
| base64 | 36 | 34 | differs |
| hex | 18 | 16 | differs |
| url | 19 | 19 | match |
| uuid | 36 | 36 | match |
Values are the marginal prompt-token cost of each string with the model's fixed overhead subtracted. An x marks a row excluded as corrupt for that model.
API surface
The declared serving contracts differ| Field | Ling-3.0-flash | Poolside: Laguna XS 2.1 | Verdict |
|---|---|---|---|
| Context length | 262144 | 262144 | ✓ match |
| Max output tokens | 32768 | 32768 | ✓ match |
| Supported parameters | frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, temperature, tool_choice, tools, top_k, top_logprobs, top_p | include_reasoning, max_tokens, reasoning, temperature, tool_choice, tools | × differs |
| Defaults | {} | {} | ✓ match |
| Reasoning contract | {"mandatory":false,"default_enabled":true} | {"mandatory":false,"default_enabled":true} | ✓ match |
| Modalities | text->text | text->text | ✓ match |
Method: tokenizer fingerprinting, v1, 50 strings. Raw data on the data page. This page is static and dated; the interactive bench compares any two of the 422 catalogue models.