Benchmarking the Efficiency of Automatically Generated Code Dong Huang
–Neural Information Processing Systems
LLMs is generally worse than the efficiency of human-written canonical solutions. For example, GPT -4 generated code has an average 3.12 times execution time that
Neural Information Processing Systems
Nov-14-2025, 01:11:55 GMT
- Country:
- Africa > Rwanda
- Asia
- Europe > Austria
- Vienna (0.14)
- North America
- Canada (0.04)
- United States
- Hawaii > Honolulu County
- Honolulu (0.04)
- Michigan > Oakland County
- Rochester (0.04)
- Virginia (0.04)
- Hawaii > Honolulu County
- Oceania > Australia
- Genre:
- Research Report > New Finding (0.93)
- Industry:
- Energy (0.92)
- Technology: