OpenAI Says GPT-6 Astra Hits 87.4% on MultiLangBench Coding Test
Summary
OpenAI reports its GPT-6 Astra model reaches an average 87.4% test pass rate on MultiLangBench across 20 programming languages, up from 26.8% for GPT-5.6 Sol. OpenAI says GPT-6.1 Sol hits 86.6% accuracy on its COBOL migration evaluation, versus 5.4% for GPT-5.6 Sol at low reasoning effort. The company says the gains could help teams maintain critical COBOL and Fortran systems.
Key Points
- OpenAI says GPT-6 Luna reaches 40.3% on MultiLangBench at an estimated $0.77 per sample, versus $3.48 for GPT-5.6 Sol.
- COBOL remains the hardest language in OpenAI's MultiLangBench results at 72.1%, the only language where GPT-6 Astra falls below 83%.
- OpenAI publishes the MultiLangBench evaluation setup and test suite on GitHub with per-language results for developers to inspect.