1
Surprise upset: GPT-5.5 beats Claude Fable 5 on brutal new Agents’ Last Exam benchmark
GPT-5.5逆袭Claude最新旗舰，在严苛Agent终考中以24%通过率胜出，模型竞争再掀波澜。
Researchers from the University of California, Berkeley's Center for Responsible, Decentralized Intelligence (RDI), alongside an advisory committ…