OpenAI publishes low-resource programming language benchmark results
What happened
On October 19, OpenAI published research and benchmark results on coding in low-resource programming languages, covering database construction and COBOL migration evaluations. In the published data, GPT‑6 Astra averaged an 87.4% test pass rate across the 20 languages in MultiLangBench; GPT‑5.6 Sol averaged 26.8%. The gap between the two models on this benchmark is 60.6 percentage points.
Written by AI from the coverage · updated 2 hours ago
Coverage
Follow the reports to see the story from different sides.
- OpenAI NewsAdvancing coding in low‑resource programming languages
OpenAI 公布低资源编程语言评测结果，GPT‑6 Astra 在 MultiLangBench 的 20 种语言上平均测试通过率达 87.4%，GPT‑5.6 Sol 为 26.8%。
Heat over time
Heat now 7·Comparable peak 7（Oct 20 08:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.