AI Desk · AI Fingerprinting · Compare
Meta: Llama 3.2 1B Instruct · Nous: Hermes 4 70B
Meta: Llama 3.2 1B Instruct recordNous: Hermes 4 70B recordOpen in the interactive bench
Tokenizer fingerprint
50 of 50 mutually clean strings agree| Test string | Meta: Llama 3.2 1B Instruct | Nous: Hermes 4 70B | 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 | 3 | 3 | match |
| digits-12 | 4 | 4 | match |
| digits-30 | 10 | 10 | match |
| digits-sep | 7 | 7 | match |
| float-long | 9 | 9 | match |
| zh-common | 12 | 12 | match |
| zh-long | 18 | 18 | match |
| zh-rare | 18 | 18 | match |
| ja-kana | 11 | 11 | match |
| ja-kanji | 12 | 12 | match |
| ko | 14 | 14 | match |
| ru | 14 | 14 | match |
| ar | 12 | 12 | match |
| he | 24 | 24 | match |
| hi | 15 | 15 | match |
| th | 14 | 14 | match |
| el | 13 | 13 | match |
| emoji-basic | 10 | 10 | match |
| emoji-skin | 30 | 30 | match |
| emoji-zwj-family | 15 | 15 | match |
| emoji-zwj-x3 | 45 | 45 | match |
| emoji-flags | 24 | 24 | match |
| emoji-prof | 26 | 26 | match |
| math | 31 | 31 | match |
| boxdraw | 23 | 23 | match |
| combining | 11 | 11 | match |
| cjk-ext-b | 13 | 13 | match |
| surrogates | 40 | 40 | match |
| zalgo | 35 | 35 | match |
| rtl-mix | 8 | 8 | match |
| py-code | 25 | 25 | match |
| py-indent | 15 | 15 | match |
| json | 20 | 20 | match |
| html | 16 | 16 | match |
| regex | 44 | 44 | match |
| camel | 5 | 5 | match |
| snake | 6 | 6 | match |
| rare-word-x5 | 31 | 31 | match |
| repeat-tok | 22 | 22 | match |
| base64 | 35 | 35 | match |
| hex | 11 | 11 | match |
| url | 17 | 17 | match |
| uuid | 27 | 27 | 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 | Meta: Llama 3.2 1B Instruct | Nous: Hermes 4 70B | Verdict |
|---|---|---|---|
| Context length | 60000 | 131072 | × differs |
| Max output tokens | – | – | ✓ match |
| Supported parameters | frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, seed, stop, temperature, top_k, top_p | frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, temperature, top_k, top_p | × differs |
| Defaults | {} | {} | ✓ match |
| Reasoning contract | – | {"mandatory":false} | × differs |
| Modalities | text->text | text->text | ✓ match |
Meta: Llama 3.2 1B Instruct: OpenRouter's listing shows 54,000 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum. Nous: Hermes 4 70B: OpenRouter's listing shows 117,964 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.
Method: tokenizer fingerprinting, v1, 50 strings. This page is static and dated; the interactive bench compares any two of the 337 measured models.