AI 导读
– https://t.co/nymq33tLqa 标题：“前沿模型物理能力如何？专家重新评分揭示评测缺陷与领先基准接近饱和”
正文
– https://t.co/nymq33tLqa
Title: "How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks"
来源：@rohanpaul_ai · x.com