The Decoder· Jonathan Kemper·· 9d agoAI score52
AI coding agents still need manual cleaning for nearly three-quarters of the tasks in practical tests
AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test
AI digest
Scholars from Alibaba and several universities in Asia have built a coding agent benchmark test, showing that even the best models have only completed a quarter of the tasks, and points out that current coding benchmarks are too simple and need tests closer to practical application scenarios.
Source:The Decoder · the-decoder.com