Генерация кода для XR-приложений достигла 96,5% точности
The new benchmark GenXR-Bench evaluated 112 tasks for XR application development, including 24 feature implementations, 21 bug repairs, and 67 application generation tasks. The testing suite achieved 96.5% accuracy against expert judgments.
#coding agents#xr development#genxr-bench#benchmarking#software engineering



