Maybe I just use GPT4 too much, but I disagree and most benchmarks show Clause being neck-and-neck with 3.5, especially the lmsys benchmarks which I think are the highest quality. [0] MMLU is basically broken (although even that puts Claude higher).
[0]: https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboar...
Maybe I just use GPT4 too much, but I disagree and most benchmarks show Clause being neck-and-neck with 3.5, especially the lmsys benchmarks which I think are the highest quality. [0] MMLU is basically broken (although even that puts Claude higher).
[0]: https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboar...