EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

TL;DR

EffiBench-X is a multi-language benchmark that evaluates the efficiency of LLM-generated code across six programming languages, revealing current models lag behind human efficiency and highlighting the need for optimization techniques.

Contribution

Introduces EffiBench-X, the first multi-language benchmark for measuring code efficiency of LLMs, with a comprehensive dataset and evaluation framework across six languages.

Findings

LLMs generate functionally correct code but are less efficient than humans.

Qwen3-32B achieves about 62% of human efficiency on average.

Efficiency varies significantly across programming languages.

Abstract

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consistently underperform human experts in efficiency. Even the most efficient LLM-generated solutions (Qwen3-32B) achieve only around \textbf{62\%} of human efficiency on average, with significant language-specific variations. LLMs show better efficiency in Python, Ruby, and JavaScript than in Java, C++, and Golang. For instance, DeepSeek-R1's Python code is significantly more efficient than its Java code. These results highlight the critical need for research into LLM optimization techniques to improve code efficiency across diverse languages. The dataset and evaluation infrastructure are submitted and available at https://github.com/EffiBench/EffiBench-X.git and https://huggingface.co/datasets/EffiBench/effibench-x.