AI Desk · Model Identity · Compare

Arcee AI: Trinity Large Thinking · Cohere: North Mini Code (free)

Identity similarity: lowDivergent fingerprints · 24/50These models tokenise differently. Divergence on the high-information strings (CJK, emoji, digits) separates unrelated vocabularies within a handful of samples.

Arcee AI: Trinity Large Thinking recordCohere: North Mini Code (free) recordOpen in the interactive bench

Tokenizer fingerprint

24 of 50 mutually clean strings agree
Test stringArcee AI: Trinity Large ThinkingCohere: North Mini Code (free)Verdict
en-prose1314differs
en-long1515match
spaces-2033match
spaces-6033match
tabs-2033match
newlines-2044match
mixed-ws56differs
digits-933match
digits-1244match
digits-301010match
digits-sep77match
float-long99match
zh-common1010match
zh-long1213differs
zh-rare1918differs
ja-kana97differs
ja-kanji119differs
ko1410differs
ru1412differs
ar1611differs
he1710differs
hi1811differs
th209differs
el1813differs
emoji-basic1010match
emoji-skin1310differs
emoji-zwj-family79differs
emoji-zwj-x32127differs
emoji-flags1212match
emoji-prof1413differs
math2424match
boxdraw2122differs
combining109differs
cjk-ext-b1616match
surrogates2835differs
zalgo2933differs
rtl-mix86differs
py-code2525match
py-indent1515match
json2020match
html1616match
regex3839differs
camel66match
snake66match
rare-word-x52120differs
repeat-tok2220differs
base642932differs
hex1010match
url1717match
uuid2727match

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
FieldArcee AI: Trinity Large ThinkingCohere: North Mini Code (free)Verdict
Context length262144256000× differs
Max output tokens26214464000× differs
Supported parametersfrequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_pfrequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, seed, stop, temperature, tool_choice, tools, top_k, top_p× differs
Defaults{"temperature":0.3,"top_p":0.8,"top_k":null,"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":true}{"mandatory":false}× differs
Modalitiestext->texttext->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.