{"list":"other","total":55,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2302.06527","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","created":"2023-02-13","cited_by_count":194},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168},{"id":"2305.04764","title":"ChatUniTest: A Framework for LLM-Based Test Generation","created":"2023-05-08","cited_by_count":96},{"id":"2408.06450","title":"Evaluating Language Models for Efficient Code Generation","created":"2024-08-12","cited_by_count":73},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62},{"id":"2503.06680","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","created":"2025-03-09","cited_by_count":58},{"id":"2202.05218","title":"Pynguin: Automated Unit Test Generation for Python","created":"2022-02-10","cited_by_count":50},{"id":"2407.21579","title":"A Performance Study of LLM-Generated Code on Leetcode","created":"2024-07-31","cited_by_count":49},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47},{"id":"2406.06647","title":"How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark","created":"2024-06-10","cited_by_count":43},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42},{"id":"2406.04531","title":"TESTEVAL: Benchmarking Large Language Models for Test Case Generation","created":"2024-06-06","cited_by_count":40},{"id":"2403.16218","title":"CoverUp: Effective High Coverage Test Generation for Python","created":"2024-03-24","cited_by_count":38},{"id":"2507.12415","title":"SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?","created":"2025-07-16","cited_by_count":36},{"id":"2402.07844","title":"Mercury: A Code Efficiency Benchmark for Code Large Language Models","created":"2024-02-12","cited_by_count":35},{"id":"2403.15852","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","created":"2024-03-23","cited_by_count":34},{"id":"2405.15189","title":"EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization","created":"2024-05-24","cited_by_count":30},{"id":"2310.01602","title":"CAT-LM: Training Language Models on Aligned Code And Tests","created":"2023-10-02","cited_by_count":28},{"id":"2407.14044","title":"ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?","created":"2024-07-19","cited_by_count":27},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27},{"id":"2401.15963","title":"NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness","created":"2024-01-29","cited_by_count":26},{"id":"2405.03786","title":"TOGLL: Correct and Strong Test Oracle Generation with LLMs","created":"2024-05-06","cited_by_count":24},{"id":"2002.07764","title":"Sampling in Software Engineering Research: A Critical Review and Guidelines","created":"2020-02-18","cited_by_count":23},{"id":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","cited_by_count":22},{"id":"2404.06041","title":"On Evaluating the Efficiency of Source Code Generated by LLMs","created":"2024-04-09","cited_by_count":21},{"id":"2502.02827","title":"COFFE: A Code Efficiency Benchmark for Code Generation","created":"2025-02-05","cited_by_count":20},{"id":"2406.03248","title":"Large Language Models as Evaluators for Recommendation Explanations","created":"2024-06-05","cited_by_count":19},{"id":"2502.18489","title":"LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness","created":"2025-02-17","cited_by_count":10},{"id":"2409.03093","title":"ASTER: Natural and Multi-language Unit Test Generation with LLMs","created":"2024-09-04","cited_by_count":9},{"id":"2508.20124","title":"Towards Better Correctness and Efficiency in Code Generation","created":"2025-08-24","cited_by_count":9},{"id":"2502.02412","title":"AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code","created":"2025-02-04","cited_by_count":8},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","cited_by_count":8},{"id":"1708.08437","title":"SlowFuzz: Automated Domain-Independent Detection of Algorithmic Complexity Vulnerabilities","created":"2017-08-28","cited_by_count":6},{"id":"2505.20324","title":"Evaluating the Energy-Efficiency of the Code Generated by LLMs","created":"2025-05-23","cited_by_count":4},{"id":"2508.03931","title":"Analyzing Prominent LLMs: An Empirical Study of Performance and Complexity in Solving LeetCode Problems","created":"2025-08-05","cited_by_count":4},{"id":"2505.23471","title":"Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency","created":"2025-05-29","cited_by_count":3},{"id":"1706.10118","title":"Navigate, Understand, Communicate: How Developers Locate Performance Bugs","created":"2017-06-30","cited_by_count":2},{"id":"2107.13320","title":"A Case Study on the Stability of Performance Tests for Serverless Applications","created":"2021-07-28","cited_by_count":2},{"id":"2505.02346","title":"An Empirical Study on the Performance and Energy Usage of Compiled Python Code","created":"2025-05-05","cited_by_count":2},{"id":"2604.26923","title":"ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation","created":"2026-04-29","cited_by_count":2},{"id":"1906.12066","title":"Pinpointing Performance Inefficiencies in Java","created":"2019-06-28","cited_by_count":1},{"id":"2408.08148","title":"Early Detection of Performance Regressions by Bridging Local Performance Data and Architectural Models","created":"2024-08-15","cited_by_count":1}],"next_cursor":null}