5 Sources
[1]
Can AI help solve the COBOL code crisis?
The ancient code holding the world together may meet its match in AI. Today is not that day. What do the IRS, banks, airlines, and government infrastructure around the world have in common? They're all running on systems propped up by antique computer code that nobody dares touch, lest everything
[2]
OpenAI says its models can help banks migrate from old COBOL programs - Engadget
The company's models are now better at working with COBOL and other old languages. OpenAI's models are now better at building and migrating software in old programming languages with a dwindling number of programmers, including COBOL, Fortran and Visual Basic. As the company explains, 40 percent
[3]
OpenAI Says Its Models Can Give the Financial Sector a Coding Makeover
Banks, government agencies, and other critical institutions run largely on antiquated programming languages. Can AI help bring them up to date? Artificial intelligence has deciphered ancient scrolls and could even help humans communicate with other animals, but now OpenAI is using the technology
[4]
GPT-6.1 Sol scores 97.9% on OpenAI's COBOL test
The COBOL benchmark requires AI models to translate programs into five modern languages while preserving their behavior exactly, including financial calculations and output formatting. OpenAI said its newest models improved sharply at writing and migrating code in languages including COBOL, with
[5]
OpenAI looks to help banks modernise legacy software their operations still depend on
OpenAI has enhanced its models to work with legacy programming languages like COBOL and Fortran. The AI assists companies in modernising critical software systems, which often lack documentation. Recent tests showed significant improvements in accuracy for building and translating software across
Share
Copy Link
OpenAI announced its GPT-6.1 Sol model achieved 97.9% accuracy in migrating COBOL programs to modern languages like Python and Java while preserving behavior. The breakthrough addresses the decades-old challenge of modernizing legacy systems that power 95% of ATM transactions and 40% of online banking systems, though experts caution production deployment still requires extensive testing.
OpenAI announced substantial improvements in its AI models' ability to work with legacy programming languages like COBOL, potentially addressing a crisis that costs the US economy an estimated $105 billion annually
1
. The company's GPT-6.1 Sol model achieved 86.6% behavior preservation accuracy at low reasoning effort when migrating COBOL programs to modern languages, climbing to 97.9% at higher reasoning settings2
. This marks a dramatic leap from GPT-5.6 Sol's mere 5.4% accuracy at the same task4
.
Source: Engadget
The breakthrough matters because COBOL, created in 1959, remains embedded in critical infrastructure worldwide
5
. According to IBM figures cited by OpenAI, COBOL supports more than 40% of online banking systems, handles 80% of in-person credit card transactions, and processes 95% of ATM transactions1
. Yet the programmers who understand these systems have largely retired or died, creating an urgent need for AI-assisted software modernization.OpenAI developed two evaluation benchmarks to measure its models' capabilities with legacy systems. MultiLangBench asks models to build SQLite-compatible database engines from scratch in 20 programming languages
4
. GPT-6 Astra achieved an average test pass rate of 87.4% across all languages, compared to 26.8% for GPT-5.6 Sol2
. COBOL remained the hardest language to crack, with Astra's pass rate reaching 72.1%4
.
Source: Gizmodo
The second benchmark tests COBOL migration to modern languages including C++, Java, Kotlin, Python, and Rust while preserving exact program behavior
3
. This requires models to maintain critical details like how COBOL rounds numbers with excess decimal digits and handles missing records—nuances that could produce different financial results even if translated code runs without errors2
. OpenAI's hidden tests require byte-for-byte parity on observable outputs, and a migration counts as successful only if all tests pass5
.Anthropic also sees opportunity in legacy systems. In February, the company published a code modernization playbook and positioned its Claude Code agent as a solution to migrate COBOL code into modern languages like Java or Python
1
. Anthropic claimed "the economics of COBOL modernization have shifted," suggesting teams could modernize codebases in quarters instead of years3
. IBM shares fell 13% following Anthropic's announcement—the company's biggest single-day slide since 2000—as investors worried about threats to IBM's mainframe business that helps companies maintain legacy systems3
.
Source: The Verge
However, Anthropic offered no performance benchmarks showing how well Claude Code could perform such migrations, unlike OpenAI's detailed testing results
1
. The competition signals growing recognition that AI-assisted software modernization represents a massive market opportunity as organizations face mounting pressure to modernize legacy software before the remaining pool of COBOL engineers disappears entirely.Related Stories
Despite OpenAI's impressive benchmarks, experts caution that these advances remain far from enabling safe replacement of critical infrastructure. "Rewriting code is not the same as replacing a system," said Vadim Zaytsev, associate professor of software evolution at the University of Twente
1
. He noted the largest system he'd seen contained 250 million lines of COBOL, and code represents only part of the challenge. Systems may use multiple languages, store data in various formats, integrate with other systems, and must meet expectations of people and organizations that depend on them1
.OpenAI spokesperson Oscar Haines acknowledged that legacy code "is still far from a solved problem" and said the company is exploring ways to build better tests and improve its models' understanding of coding languages
1
. The company emphasized that applying behavior-preserving capabilities to production software still requires expert review and testing against business rules and dependencies2
.The short-term implication is that financial institutions and government agencies now have AI tools capable of assisting with code modernization, though not replacing human expertise. Banks that still rely on COBOL systems face mounting pressure as COBOL programmers age out of the workforce, making migration increasingly urgent
2
. Organizations should begin pilot programs testing these AI capabilities on non-critical systems while maintaining rigorous human oversight.Longer-term, the question is whether AI models can eventually handle the full complexity of production legacy systems. OpenAI's GPT-6.1 Sol costs 61% less than GPT-5.6 Sol while delivering dramatically better results, suggesting economic viability is improving
4
. However, the gap between 98% accuracy in controlled tests and the 100% reliability required for banking systems and critical infrastructure remains significant. Watch for how quickly organizations move beyond pilot programs to production deployments, and whether any major COBOL migration failures emerge as early adopters test these tools at scale.Summarized by
Navi
[1]
[4]