NEWS · MODELS · #2577
OpenAI reports strong internal results for GPT-6.1 Sol migrating COBOL to modern languages
OpenAI published a blog post reporting that its GPT-6.1 Sol model achieved 87% behavior-preservation accuracy on COBOL-to-modern-language migrations at low reasoning effort and up to 98% at higher effort in its internal tests, and said migrations are judged successful only if all tests pass. The article notes Anthropic has promoted a COBOL modernization playbook and Claude Code without public benchmarks, and experts cautioned these results do not yet solve the broader, risky engineering challenge of replacing critical legacy systems.
KEY POINTS
- OpenAI published a blog post reporting that its GPT-6.1 Sol model achieved 87% behavior-preservation accuracy on COBOL-to-modern-language migrations at low reasoning effort and up to 98% at higher effort in its internal tests, and said migrations are judged successful only if all tests pass.
- The article notes Anthropic has promoted a COBOL modernization playbook and Claude Code without public benchmarks, and experts cautioned these results do not yet solve the broader, risky engineering challenge of replacing critical legacy systems.
- If validated and generalizable, reliable AI-driven COBOL migration could lower costs and risks of modernizing critical infrastructure, but the results are internal and experts warn migration is distinct from safely replacing whole systems.
WHY IT MATTERS
If validated and generalizable, reliable AI-driven COBOL migration could lower costs and risks of modernizing critical infrastructure, but the results are internal and experts warn migration is distinct from safely replacing whole systems.