OpenAI reports GPT-6.1 Sol gains in legacy-language coding and COBOL migration, per its MultiLangBench results
OpenAI says its newer models are much better at writing and migrating code in legacy languages such as COBOL, Fortran and Visual Basic. The company cites the importance of these languages to critical infrastructure: COBOL reportedly supports over 40% of online banking systems, 80% of in-person card transactions and 95% of ATM transactions. On its self-built MultiLangBench, GPT-6 Astra reached an 87.4% average test pass rate, up from 26.8% for GPT-5.6 Sol, with COBOL rising from 10.9% to 72.1% and Fortran from 21.4% to 83.5%. In COBOL migration tests to C++, Java, Kotlin, Python or Rust, GPT-6.1 Sol reached 86.6% accuracy at low reasoning effort and 97.9% at higher effort. The figures are vendor-reported, and production migrations would still need expert review and testing. This is product news with no direct threat. The article also teases the Blue Report 2026, which says only 37% of attacker actions are blocked once valid credentials are in use, based on 338 million simulations.
Linha do tempo
-
OpenAI reports GPT-6.1 Sol gains in legacy-language coding and COBOL migration, per its MultiLangBench results
ler a análise desta fonte ocultar
OpenAI says its newer models are much better at writing and migrating code in legacy languages such as COBOL, Fortran and Visual Basic. The company cites the importance of these languages to critical infrastructure: COBOL reportedly supports over 40% of online banking systems, 80% of in-person card transactions and 95% of ATM transactions. On its self-built MultiLangBench, GPT-6 Astra reached an 87.4% average test pass rate, up from 26.8% for GPT-5.6 Sol, with COBOL rising from 10.9% to 72.1% and Fortran from 21.4% to 83.5%. In COBOL migration tests to C++, Java, Kotlin, Python or Rust, GPT-6.1 Sol reached 86.6% accuracy at low reasoning effort and 97.9% at higher effort. The figures are vendor-reported, and production migrations would still need expert review and testing. This is product news with no direct threat. The article also teases the Blue Report 2026, which says only 37% of attacker actions are blocked once valid credentials are in use, based on 338 million simulations.