The Hidden Setting That’s Rewriting Every AI Benchmark This Year
中文摘要
GPT-6 Astra、GPT-5.6 Sol 和 Claude Opus 5 等模型在基准测试中遭遇共同瓶颈，其原因尚未得到充分解释。
English Summary
GPT-6 Astra, GPT-5.6 Sol, and Claude Opus 5 are hitting a common performance wall in benchmarks, a phenomenon that remains largely unexplained.
原文节选
GPT-6 Astra, GPT-5.6 Sol, and Claude Opus 5 all hit the same wall this year, and almost nobody explained why. Continue reading on Generative AI »