BigO(Bench): Can LLMs Generate Code with Controlled Time and Space Complexity?

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2503.15242v3 Announce Type: replace-cross Abstract: We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and space complexities. This benchmark addresses the gap in…

ai science

Sources

T1BigO(Bench): Can LLMs Generate Code with Controlled Time and Space Complexity?arXiv24 Sept, 04:00