|
|
|
|
|
|
by atemerev
434 days ago
|
|
|
There is no OpenAI model better than R1, reasoning or not (as confirmed by the same Aider benchmark; non-coding tests are less objective, but I think it still holds). With Gemini (current SOTA) and Sonnet (great potential, but tends to overengineer/overdo things) it is debatable, they are probably better than R1 (and all OpenAI models by extension). |
|
|