OpenAI称GPT-6大幅提升COBOL、Fortran等遗留语言能力
原标题：OpenAI says GPT-6 is much better with legacy programming languages such as COBOL and Fortran
AI 摘要
OpenAI 表示其最新模型 GPT-6 系列在 COBOL、Fortran、Visual Basic 等低资源编程语言上的能力显著提升，并为此构建了 MultiLangBench 和 COBOL 迁移两个评测基准。在 MultiLangBench 上，GPT-6 Astra 在 20 种语言中的平均测试通过率达 87.4%，远高于 GPT-5.6 Terra 的约 38%；在 COBOL 转 C++、Java、Kotlin、Python 或 Rust 的迁移基准上，GPT-6.1 Sol 在低推理强度下准确率为 86.6%，而 GPT-5.6 Sol 仅为 5.4%，提高推理强度后可达 97.9%。OpenAI 称这些语言支撑着全球关键基础设施，IBM 估计 COBOL 驱动超过 40% 的网上银行系统和 95% 的 ATM 交易。
正文节选
OpenAI says GPT-6 is much better with legacy programming languages such as COBOL and Fortran OpenAI improved its latest AI models for "low-resource" languages like COBOL, Fortran, and Visual Basic. These languages have far less available training code than something like Python, but according to OpenAI, they prop up critical infrastructure worldwide. IBM estimates that COBOL powers more than 40 percent of online banking systems and 95 percent of all ATM transactions. OpenAI built two evaluations