Skip to content
NewA calmer, faster ZeroHour
StoryAI researchinfo

OpenAI says GPT-6 models improve legacy-language coding and COBOL migration

3 sources · 3 articlesFirst reported Updated ()
What's new

First merged summary.

Merged summary · x-ai/grok-4.7 · rewritten as coverage arrivesSummaries by Vani AI

OpenAI reports GPT-6 Astra at 87.4% on MultiLangBench, with COBOL migration near 98% at higher effort, still needing expert review.

OpenAI says newer models write and migrate software in low-resource languages, including COBOL, Fortran and Visual Basic, which it links to critical systems. On MultiLangBench, models must build a SQLite-compatible database engine across 20 languages; GPT-6 Astra averaged 87.4%, up from 26.8% for GPT-5.6 Sol. A separate COBOL migration test requires byte-for-byte output parity; GPT-6.1 Sol scored 86.6% at low effort and 97.9% at higher effort, versus 5.4% for GPT-5.6 Sol. OpenAI is releasing the benchmark setup and results on GitHub and says production migrations still need expert review.

Key facts
  • Astra scored 72.1% on COBOL, 83.5% on Fortran and 89.4% on Visual Basic.
  • BleepingComputer reports earlier rates of 10.9%, 21.4% and 27.5% for those languages.
  • GPT-6 Luna averaged 40.3% at about 78% lower estimated API cost than GPT-5.6 Sol.
  • The Decoder cites IBM: COBOL behind over 40% of online banking and 95% of ATMs.
  • OpenAI News says COBOL was Astra’s hardest MultiLangBench language, at 72%.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

What each outlet adds

beyond the shared facts
  • OpenAI NewsLuna cost estimate and GitHub release of MultiLangBench.
  • The DecoderIBM banking and ATM figures; GPT-5.6 Terra near 38%.
  • BleepingComputerPrior pass rates and OCaml rise from 25.6% to 85.8%.
Vendors
OpenAI
Products
MultiLangBench
Organizations
OpenAIIBM
AI models
GPT-6 AstraGPT-6 LunaGPT-6.1 SolGPT-5.6 TerraGPT-5.6 Sol

Coverage

oldest first · one row per article · UTC
  1. · 6d ago OpenAI NewsFirst report

    OpenAI reports coding gains on COBOL, Fortran and Visual Basic

    On OpenAI’s tests, GPT-6 Astra averaged 87.4% on MultiLangBench, up from 26.8% for GPT-5.6 Sol.

  2. · 5d ago The Decoder

    OpenAI says GPT-6 is much better at COBOL and Fortran

    GPT-6 Astra averages 87.4 percent on MultiLangBench, versus about 38 percent for GPT-5.6 Terra.

  3. · 5d ago BleepingComputer

    OpenAI says GPT-6.1 Sol is far better at migrating legacy code

    OpenAI's own MultiLangBench shows GPT-6.1 Sol at 86.6% COBOL migration accuracy versus 5.4% for GPT-5.6 Sol.