https://x.com/artificialanlys/status/1859614633654616310?s=46
Wait - is the new GPT-4o a smaller and less intelligent model?
— Artificial Analysis (@ArtificialAnlys) November 21, 2024
We have completed running our independent evals on OpenAI’s GPT-4o release yesterday and are consistently measuring materially lower eval scores than the August release of GPT-4o.
GPT-4o (Nov) vs GPT-4o (Aug):
➤… pic.twitter.com/gjY2pBFuUv
이 글에 따르면 원래 4o보다 성능은 낮아진 대신 속도는 빨라졌다는거 같음
이러면 llm 아레나는 뭐지?
아레나 = 인기투표