---
title: "OpenAI says its newest models handle COBOL and Fortran far better, and releases a 20-language coding test"
url: https://anawords.com/story/openai-cobol-fortran-coding-multilangbench-results
published: 2026-10-20T13:01:16+05:30
updated: 2026-10-20T13:01:16+05:30
section: Models & Launches
author: Mayank Sahu
checked: sources checked by AI, approved by editor
version: 1
---

# OpenAI says its newest models handle COBOL and Fortran far better, and releases a 20-language coding test

In OpenAI’s own tests, GPT-6.1 Sol migrated COBOL programs correctly 86.6% of the time at low effort, up from 5.4%. The MultiLangBench test is public; the migration test is not.

**In short:** OpenAI published results on 19 October 2026 showing its newest models perform much better on less common programming languages such as COBOL and Fortran. In its own COBOL migration test, GPT-6.1 Sol scored 86.6% at low reasoning effort and 97.9% at higher effort, against 5.4% for GPT-5.6 Sol.

## What OpenAI published

OpenAI’s post, “Advancing coding in low-resource programming languages”, covers languages with less public code for models to learn from, such as COBOL, Fortran and Visual Basic.[^1] Many banks, insurers and governments still run core systems in them.

It introduces two tests.[^1][^2]

- **MultiLangBench**: models build a SQLite-compatible database engine from scratch in each of 20 languages, scored by test pass rate.
- **COBOL migration**: models translate COBOL programs into C++, Java, Kotlin, Python or Rust. A migration only counts if every hidden test passes.

## The results (OpenAI’s own measurements)

- **GPT-6 Astra** averaged 87.4% on MultiLangBench, up from 26.8% for GPT-5.6 Sol. Its lowest language was COBOL, at 72.1%.[^1][^2]
- **GPT-6 Luna** averaged 40.3%, at an estimated $0.77 per sample against $3.48 for GPT-5.6 Sol.[^1][^2]
- **GPT-6.1 Sol** scored 86.6% on COBOL migration at low reasoning effort and 97.9% at higher effort, versus 5.4% for GPT-5.6 Sol at low effort.[^1][^2]

## What is open, and what to keep in mind

OpenAI released MultiLangBench’s setup, tests and per-language results on GitHub.[^1] The COBOL migration test was not released.[^2]

OpenAI ran both tests, so these are vendor results until others reproduce them.[^2] OpenAI itself says real migrations still need expert review and testing against business rules.[^2] Small differences matter in this kind of code: a rewrite that rounds decimals differently can run without errors and still change financial results.[^2]

## Why it matters

Legacy systems are expensive to maintain and hard to staff. Better tools for reading and moving old code could help, as long as testing stays rigorous.

## Fact ledger

- [Confirmed] OpenAI published results on low-resource programming languages on 19 October 2026. (source 1)
- [Confirmed] MultiLangBench asks models to build a SQLite-compatible engine in 20 languages. (source 1)
- [Company claim] GPT-6 Astra averaged 87.4% on MultiLangBench, up from 26.8% for GPT-5.6 Sol. (source 1,2)
- [Company claim] GPT-6.1 Sol scored 86.6% (low effort) and 97.9% (higher effort) on COBOL migration. (source 1,2)
- [Confirmed] MultiLangBench is released on GitHub. (source 1)
- [Unconfirmed] The COBOL migration test is not public. (source 2)

## Sources

1. [OpenAI: Advancing coding in low-resource programming languages](https://openai.com/index/low-resource-programming-languages/) — official
2. [CellCog blog: OpenAI’s COBOL test, 5.4% to 86.6% in one model jump](https://cellcog.ai/blog/openai-cobol-low-resource-languages/)