We used an AI judge and a human to rank the results.
Why not try some of the open weight models? Kimi K2 Thinking supposedly is almost as good as GPT-5, better than Sonnet 4.5, and $0.60 vs $3.
always loved reading your newsletters
Why not try some of the open weight models? Kimi K2 Thinking supposedly is almost as good as GPT-5, better than Sonnet 4.5, and $0.60 vs $3.
always loved reading your newsletters