Bright key facts / Demonstrated
OpenAI’s COBOL AI gains put legacy software in focus
New coding results invite a serious look at AI-assisted maintenance. Bright examines the evidence, the limits and what safer modernization would require.
- AI’s role
- OpenAI evaluates code translation and SQLite-compatible database implementations across programming languages.
- Documented result
- OpenAI reports 86.6% COBOL migration accuracy for GPT-6.1 Sol at low reasoning effort and 97.9% at higher effort; GPT-6 Astra averaged an 87.4% MultiLangBench test pass rate at maximum effort across 20 languages. The measurements use different denominators.
- Important limitation
- Company-reported benchmark results; not independently reproduced by Bright.