top | item 43595793 (no title) redlock | 11 months ago Doesn't OpenRouter ranking include pricing?Not really a good measure of quality or performance but of cost effectiveness discuss order hn newest mbesto|11 months 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"
mbesto|11 months 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"
mbesto|11 months ago
"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"