OpenAI says GPT-6 is much better at COBOL and Fortran
Original title: OpenAI says GPT-6 is much better with legacy programming languages such as COBOL and Fortran
GPT-6 Astra averages 87.4 percent on MultiLangBench, versus about 38 percent for GPT-5.6 Terra.
OpenAI says it improved its latest models for low-resource languages including COBOL, Fortran and Visual Basic, which it says support critical infrastructure. MultiLangBench asks models to build a SQLite-compatible database engine; with maximum reasoning, GPT-6 Astra averages 87.4 percent across 20 languages. On a COBOL migration benchmark, GPT-6.1 Sol reaches 86.6 percent at low reasoning effort and 97.9 percent at higher effort, against 5.4 percent for GPT-5.6 Sol.
Unconfirmed: Pass rates are OpenAI's own results, and the COBOL infrastructure share is an IBM estimate cited by OpenAI.
- IBM estimates COBOL powers more than 40 percent of online banking systems.
- The same IBM estimate puts COBOL behind 95 percent of ATM transactions.
- GPT-6 Luna scores 40.3 percent, just above GPT-5.6 Terra at 37.9 percent.
- GPT-6 Astra and GPT-6.1 Sol both reach about 87 percent on MultiLangBench.
- Products
- MultiLangBench
From the original article
1 min read at the-decoder.com
OpenAI improved its latest models for low-resource programming languages like COBOL, Fortran, and Visual Basic. On the new MultiLangBench, GPT-6 Astra hits an 87. 4 percent test pass rate across 20 languages, up from about 38 percent for GPT-5.
By Matthias Bastian · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.