DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation

August 31, 2026 ยท Grace Period ยท ๐Ÿ› EMNLP 2026 Main Conference

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Zhihao Gong, Junzhe Yu, Dong Huang, Zeyu Sun, Jie M. Zhang, Dan Hao arXiv ID 2608.30248 Category cs.SE: Software Engineering Citations 0 Venue EMNLP 2026 Main Conference
Abstract
Current data science (DS) code generation benchmarks equate correctness with quality, overlooking execution time differences that span orders of magnitude between correct solutions. We introduce DSEffi-Bench, the first benchmark specifically targeting execution efficiency in LLM-generated DS code, comprising 1,000 instances across 10+ DS libraries with stress-testing harnesses and human-validated references. Evaluating 16 models across 3 tiers, we find that correctness alone fails to characterize efficiency: GPT-5.4 leads in correctness (Pass, 66.9\%) but its efficiency score (B$|$P, 71.7\%) nearly matches GPT-5.4-mini (71.6\%), which solves 47 fewer tasks; Kimi-K2.5 ranks lowest in correctness among frontier models (40.2\%) yet achieves the highest efficiency score (73.6\%) across all 16 models. A human-annotated five-category taxonomy reveals that 79.1\% of efficiency deficits extend beyond algorithmic complexity to domain-specific root causes, with distinct failure profiles across model tiers and libraries. Two exploratory experiments provide initial evidence that these diagnostics can guide improvement, yielding up to +14.7\% efficiency gains via taxonomy-guided optimization and approaching Claude-Opus-4.6 Best@3 in efficiency at 13.0$\times$ lower cost via library-conditioned routing.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Software Engineering