Surprise upset: GPT-5.5 beats Claude Fable 5 on brutal new Agents’ Last Exam benchmark (opens in new tab)

Researchers from the University of California, Berkeley's Center for Responsible, Decentralized Intelligence (RDI), alongside an advisory committee of over 300 domain experts, have —a grueling new benchmark built to measure whether artificial intelligence can actually execute economically valuable, long-horizon professional workflows.In a shocking upset, operating through the Codex harness, secured the absolute top spot on the new with a 24.0% pass rate, beating Anthropic's highly anticipated...