# The Decoder — OpenAI says GPT-6 is much better with legacy programming languages such as COBOL and Fortran

- Company: The Decoder (the-decoder.com)
- Announced: 2026-10-20T16:40:29+00:00
- Category: model-update
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://the-decoder.com/openai-says-gpt-6-is-much-better-with-legacy-programming-languages-such-as-cobol-and-fortran/
- Record: https://forck.live/items/25333-openai-says-gpt-6-is-much-better-with-legacy-programming-languages-such-as
- Subject: Reporting
- Models affected: GPT-6, GPT-6 Astra, GPT-5.6 Terra, GPT-6 Luna, GPT-6.1 Sol, GPT-5.6 Sol

OpenAI says its latest models handle legacy programming languages such as COBOL, Fortran and Visual Basic far better than earlier versions, languages that carry little training code but underpin critical infrastructure. IBM estimates COBOL powers more than 40 percent of online banking systems and 95 percent of all ATM transactions, according to the report. OpenAI built two evaluations to measure the progress: MultiLangBench, which asks models to build a SQLite-compatible database engine from scratch, and a COBOL migration benchmark that translates COBOL into C++, Java, Kotlin, Python or Rust. On MultiLangBench at maximum reasoning effort, GPT-6 Astra reaches an average test pass rate of 87.4 percent across 20 languages, up from about 38 percent for GPT-5.6 Terra, while GPT-6 Luna scores 40.3 percent, barely ahead of GPT-5.6 Terra at 37.9 percent but at a much lower cost. On the COBOL migration benchmark, GPT-6.1 Sol reaches 86.6 percent accuracy at low reasoning effort against 5.4 percent for GPT-5.6 Sol, and raising reasoning effort pushes accuracy to 97.9 percent.

## Evidence

Verbatim from https://the-decoder.com/openai-says-gpt-6-is-much-better-with-legacy-programming-languages-such-as-cobol-and-fortran/:

> On the COBOL migration benchmark, which translates COBOL into C++, Java, Kotlin, Python, or Rust, GPT-6.1 Sol reaches 86.6 percent accuracy at low reasoning effort, compared to 5.4 percent for GPT-5.6 Sol. Cranking up reasoning effort pushes accuracy to 97.9 percent.

---

Record: https://forck.live/items/25333-openai-says-gpt-6-is-much-better-with-legacy-programming-languages-such-as
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md