LLM-generated Python solutions typically consume more energy than canonical human-written solutions, with DeepSeek-v3 and GPT-4o the most efficient LLMs and worst-case gaps near 450 times on certain problems.
Effibench: Benchmarking the efficiency of automatically generated code
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Evaluating the Energy-Efficiency of the Code Generated by LLMs
LLM-generated Python solutions typically consume more energy than canonical human-written solutions, with DeepSeek-v3 and GPT-4o the most efficient LLMs and worst-case gaps near 450 times on certain problems.