Announcement
OpenAI advances legacy code understanding for COBOL, Fortran, and Visual Basic modernization
OpenAI reports GPT-6.1 Sol reached 86.6% accuracy versus GPT-5.6 Sol's 5.4% on its COBOL migration evaluation at low reasoning effort.
TLDR
OpenAI says its latest models are better at building and migrating software in languages such as COBOL, Fortran and Visual Basic. On its 20-language SQLite-building benchmark, GPT-6 Astra averaged an 87.4% test pass rate, up from 26.8% for GPT-5.6 Sol. Its COBOL migration evaluation tests whether rewritten programs preserve their behavior. OpenAI says production migrations still require expert review and testing.
Combined views
229.8K
2 Sources, first seen ago
