|
|
|
|
|
|
by mbesto
439 days ago
|
|
|
I mean it literally says on the page: "Shown are the sum of prompt and completion tokens per model, normalized using the GPT-4 tokenizer." Also, it ranks the use of Llama that is provided by cloud providers (for example, AWS Lamda). I get that OpenRouter is imperfect but its a good proxy to objectively make a claim that an LLM is "the weakest ever" |
|
|