Great summary! Please if possible could you add the context window of each model, how many tokens can you use for each?
Also, I default to 4.1 for most non complex coding tasks because it’s fast, o3 is too slow, and 4o is too sycophantic (even when you use a good system prompt 4o is so annoying sometimes).
Great summary! Please if possible could you add the context window of each model, how many tokens can you use for each?
Also, I default to 4.1 for most non complex coding tasks because it’s fast, o3 is too slow, and 4o is too sycophantic (even when you use a good system prompt 4o is so annoying sometimes).
Interesting that you say 4.1 not 4.5, does 4.1 seem noticeably better for non-complex coding tasks generally?