OpenAI says its models now come with better COBOL capabilities.
OpenAI announced significant performance improvements in its models for programming languages with relatively little code and ...
On October 19, 2026, OpenAI's official website announced an initiative to improve coding capabilities in "programming ...
OpenAI reports an 87.4% average test pass rate for GPT-6 Astra on MultiLangBench, its new 20-language COBOL and Fortran ...
Interesting Engineering on MSN
OpenAI models make huge gains in modernizing decades-old software with 97.9% accuracy
OpenAI has significantly improved its models’ ability to write software in older programming languages ...
On October 19, 2026, an announcement posted by OpenAI on X caught my eye. It stated that the latest AI models are now capable ...
OpenAI has released results for MultiLangBench, which asks models to build a SQLite-compatible engine in 20 languages, and ...
OpenAI's latest models show 86.6%-97.9% accuracy in COBOL migration, a critical language for 40% of banking systems and 800B ...
Customer stories Events & webinars Ebooks & reports Business insights GitHub Skills ...
米OpenAIは10月19日、COBOLやFortran、 Visual Basic など学習データの少ない言語でのコーディング性能向上を発表した。新ベンチマーク「MultiLangBench」で GPT-6 Astra のCOBOL合格率は10.9 ...
2026年10月20日，OpenAI宣布推出名为MultiLangBench的开源多语言编程评测框架，旨在提高低资源编程语言的编码能力。这些低资源语言，如COBOL、Fortran和VisualBasic等，虽然可用代码和文档远少于流行语言如Python和Java，但在关键基础设施中扮演着重要角色。 MultiLangBench覆盖20种编程语言，评测模型在从零构建兼容SQLite的数据库引擎时的 ...
A OpenAI divulgou na segunda-feira, 19, avanços de inteligência artificial em COBOL, Fortran e Visual Basic, linguagens de ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results