AI Desk · Model Identity · Compare
Nex AGI: Nex-N2-Mini · Qwen: Qwen3.5 Plus 2026-04-20
Identity similarity: lowDivergent fingerprints · 27/27These models tokenise differently. Divergence on the high-information strings (CJK, emoji, digits) separates unrelated vocabularies within a handful of samples.
Nex AGI: Nex-N2-Mini recordQwen: Qwen3.5 Plus 2026-04-20 recordOpen in the interactive bench
Tokenizer fingerprint
27 of 27 mutually clean strings agree| Test string | Nex AGI: Nex-N2-Mini | Qwen: Qwen3.5 Plus 2026-04-20 | Verdict |
|---|---|---|---|
| en-prose | 14 | 14 | match |
| en-long | 16 | 16 | match |
| spaces-20 | 3 | 3 | match |
| spaces-60 | 3 | 3 | match |
| tabs-20 | 3 | 3 | match |
| newlines-20 | 4 | 4 | match |
| mixed-ws | 5 | 5 | match |
| 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 | 9 | match |
| zh-long | 10 | 10 | match |
| zh-rare | 18 | 18 | match |
| ja-kana | 7 | 7 | match |
| ja-kanji | 10 | 10 | match |
| ko | 13 | 13 | match |
| ru | 12 | 12 | match |
| ar | 10 | 10 | match |
| he | 14 | 14 | match |
| hi | 15 | 15 | match |
| th | 8 | 8 | match |
| el | 13 | 13 | match |
| emoji-basic | 9 | 9 | match |
| emoji-skin | 30 | 30 | match |
| emoji-zwj-family | 18 | 18 | match |
| emoji-zwj-x3 | 54 | x | – |
| emoji-flags | 24 | x | – |
| emoji-prof | 29 | x | – |
| math | 29 | x | – |
| boxdraw | 28 | x | – |
| combining | 5 | x | – |
| cjk-ext-b | 13 | x | – |
| surrogates | 40 | x | – |
| zalgo | 36 | x | – |
| rtl-mix | 6 | x | – |
| py-code | 26 | x | – |
| py-indent | 18 | x | – |
| json | 25 | x | – |
| html | 16 | x | – |
| regex | 44 | x | – |
| camel | 5 | x | – |
| snake | 6 | x | – |
| rare-word-x5 | 30 | x | – |
| repeat-tok | 21 | x | – |
| base64 | 36 | x | – |
| hex | 17 | x | – |
| url | 19 | x | – |
| uuid | 36 | x | – |
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 | Nex AGI: Nex-N2-Mini | Qwen: Qwen3.5 Plus 2026-04-20 | Verdict |
|---|---|---|---|
| Context length | 262144 | 1000000 | × differs |
| Max output tokens | 262144 | 65536 | × differs |
| Supported parameters | include_reasoning, logprobs, max_tokens, reasoning, response_format, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p | frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p | × differs |
| Defaults | {"temperature":0.7,"top_p":0.95,"top_k":40,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null} | {} | × differs |
| Reasoning contract | {"mandatory":false} | {"mandatory":false} | ✓ match |
| Modalities | text+image->text | text+image+video->text | × differs |
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.