AI Desk · Model Identity · Compare

Nex AGI: Nex-N2-Pro · Qwen: Qwen3.7 Flash

Identity similarity: very highExact tokenizer agreement · 50/50Exact agreement across every measured string is strong evidence of shared tokenizer lineage. It shows shared ancestry, and does not on its own establish that these are the same release.

Nex AGI: Nex-N2-Pro recordQwen: Qwen3.7 Flash recordOpen in the interactive bench

Tokenizer fingerprint

50 of 50 mutually clean strings agree
Test stringNex AGI: Nex-N2-ProQwen: Qwen3.7 FlashVerdict
en-prose1414match
en-long1616match
spaces-2033match
spaces-6033match
tabs-2033match
newlines-2044match
mixed-ws55match
digits-999match
digits-121212match
digits-303030match
digits-sep1212match
float-long2222match
zh-common99match
zh-long1010match
zh-rare1818match
ja-kana77match
ja-kanji1010match
ko1313match
ru1212match
ar1010match
he1414match
hi1515match
th88match
el1313match
emoji-basic99match
emoji-skin3030match
emoji-zwj-family1818match
emoji-zwj-x35454match
emoji-flags2424match
emoji-prof2929match
math2929match
boxdraw2828match
combining55match
cjk-ext-b1313match
surrogates4040match
zalgo3636match
rtl-mix66match
py-code2626match
py-indent1818match
json2525match
html1616match
regex4444match
camel55match
snake66match
rare-word-x53030match
repeat-tok2121match
base643636match
hex1717match
url1919match
uuid3636match

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
FieldNex AGI: Nex-N2-ProQwen: Qwen3.7 FlashVerdict
Context length2621441000000× differs
Max output tokens26214465536× differs
Supported parametersfrequency_penalty, include_reasoning, logprobs, max_tokens, reasoning, temperature, tool_choice, tools, top_k, top_logprobs, top_pinclude_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, temperature, tool_choice, tools, 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}{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}× differs
Reasoning contract{"mandatory":false}{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}× differs
Modalitiestext+image->texttext+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.