OpenAI says its newest models are far better at building and migrating code in COBOL, Fortran and other low resource languages
Our latest model advances bring stronger capabilities for building and migrating software in low-resource programming languages such as COBOL, Fortran, and Visual Basic. These languages power software that banks, governments, and businesses depend on. Progress here means understanding decades of business logic and helping developers modernize those systems while preserving what works. We’re building these capabilities around the challenges developers and enterprise customers bring us. If your team is working on these systems, tell us which languages and workflows we should tackle next.
Context
Much of the software behind banks, payments and governments is written in old languages that coding models have struggled with, so reliable migration help could open a large enterprise market.
The benchmark figures are self reported by OpenAI on two evaluations it built itself, MultiLangBench and a COBOL migration test. OpenAI calls these languages low resource because there is much less public code and documentation for models to learn from than for Python or JavaScript.
Deep dive
On October 19, OpenAI posted that its latest model advances bring stronger capabilities for building and migrating software in low resource programming languages such as COBOL, Fortran and Visual Basic, which it said power software that banks, governments and businesses depend on. It asked teams working on these systems which languages and workflows it should tackle next.
In its accompanying post, OpenAI described two evaluations. MultiLangBench asks a model to build a SQLite compatible database engine from scratch in one of 20 languages, checked against tests adapted from SQLite's own suite. OpenAI said GPT 6 Astra reached an average pass rate of 87.4 percent across the 20 languages at maximum reasoning effort, up from 26.8 percent for GPT 5.6 Sol, with COBOL rising from 10.9 to 72.1 percent, Fortran from 21.4 to 83.5 percent, OCaml from 25.6 to 85.8 percent and Visual Basic from 27.5 to 89.4 percent. COBOL remained the hardest language.
The second evaluation tests migrating existing COBOL programs to another language while keeping their behavior. OpenAI said GPT 6.1 Sol scored 86.6 percent at low reasoning effort, against 5.4 percent for GPT 5.6 Sol, at 39 percent lower cost, and 97.9 percent at higher effort, which it said nearly saturates the test. It said the work was guided by developers and enterprise customers who told it coding models often struggle with these languages.
Crypto Briefing noted that Anthropic and IBM are also pursuing COBOL modernization.
What to expect next
These are OpenAI's own evaluations, so the key test is whether independent teams and enterprise customers see similar results on real legacy systems, where undocumented business rules and dialects are common. Watch whether OpenAI publishes the MultiLangBench setup so others can rerun it, which coverage of the announcement says it plans to do, and whether banks or government agencies announce migrations using these models. Also watch how Anthropic and IBM respond in the same market.