YFarmX

AI Desk · Model Identity · Compare

MythoMax 13B · ReMM SLERP 13B

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.

MythoMax 13B recordReMM SLERP 13B recordOpen in the interactive bench

Tokenizer fingerprint

50 of 50 mutually clean strings agree
Test stringMythoMax 13BReMM SLERP 13BVerdict
en-prose1616match
en-long1818match
spaces-2044match
spaces-6066match
tabs-202222match
newlines-202222match
mixed-ws99match
digits-999match
digits-121212match
digits-303030match
digits-sep1212match
float-long2222match
zh-common2222match
zh-long3434match
zh-rare2727match
ja-kana1616match
ja-kanji1616match
ko2929match
ru1414match
ar2929match
he2626match
hi3131match
th2626match
el3333match
emoji-basic2020match
emoji-skin4040match
emoji-zwj-family1919match
emoji-zwj-x35757match
emoji-flags3232match
emoji-prof3535match
math2626match
boxdraw1717match
combining1010match
cjk-ext-b1616match
surrogates5454match
zalgo3535match
rtl-mix1313match
py-code2828match
py-indent1919match
json2828match
html1717match
regex5252match
camel88match
snake1212match
rare-word-x54646match
repeat-tok4141match
base644141match
hex2020match
url2323match
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
FieldMythoMax 13BReMM SLERP 13BVerdict
Context length81926144× differs
Max output tokens36865529× differs
Supported parametersfrequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_a, top_k, top_logprobs, top_pfrequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_a, top_k, top_logprobs, top_p✓ match
Defaults{}{}✓ match
Reasoning contract✓ match
Modalitiestext->texttext->text✓ match

Method: tokenizer fingerprinting, v1, 50 strings. This page is static and dated; the interactive bench compares any two of the 486 catalogue models.