zlacker

Doesn't OpenRouter ranking include pricing?

Not really a good measure of quality or performance but of cost effectiveness

>>redloc+(OP)
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"