EffiBench-X
Emerging7papers using it
348HF downloads
1HF likes
2024first seen
Dataset Card for EffiBench-X EffiBench-X is the first multi-language benchmark designed specifically to evaluate the efficiency of LLM-generated code across six programming languages: Python, C++, Java, JavaScript, Ruby, and Golang. The dataset comprises 623 competitive programming problems paired with human expert sol
π€ Hugging Faceβ apache-2.0
Papers using EffiBench-X (7)
- EffiBench: Benchmarking the Efficiency of Automatically Generated CodeEffiSkill: Agent Skill Based Automated Code Efficiency OptimizationControlled Self-Evolution for Algorithmic Code OptimizationMulti-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model StrengthsEffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated CodeEffiLearner: Enhancing Efficiency of Generated Code via Self-OptimizationControlled Self-Evolution for Algorithmic Code Optimization