# RuntimeWire — OpenAI reports benchmark gains for COBOL and other legacy-language coding

- Company: RuntimeWire (runtimewire.com)
- Announced: 2026-10-20T03:14:01+00:00
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://runtimewire.com/article/openai-low-resource-language-coding-benchmarks
- Record: https://forck.live/items/25032-openai-reports-benchmark-gains-for-cobol-and-other-legacy-language-coding
- Subject: Reporting

OpenAI says its latest models have improved at writing and migrating code in COBOL, Fortran and Visual Basic, languages still embedded in financial and other business systems. In an October 19th post on X, the company described the work as a capability update rather than a standalone product. Its technical account says developers can try the models on coding tasks through OpenAI's API. The results matter because COBOL migration tests whether coding models can preserve business behavior across costly modernization projects. OpenAI's gains are reported on its own evaluations, and the account notes that production safety and enterprise adoption remain unresolved.

## Evidence

Verbatim from https://runtimewire.com/article/openai-low-resource-language-coding-benchmarks:

> OpenAI says its latest models have improved at writing and migrating code in COBOL, Fortran and Visual Basic, targeting languages that remain embedded in financial and other business systems. In an October 19th post on X , the company described the work as a capability update; it did not announce a standalone product.

---

Record: https://forck.live/items/25032-openai-reports-benchmark-gains-for-cobol-and-other-legacy-language-coding
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md