The findings show that, while LLMs achieve promising results, they struggle with harder problems and with programming languages that have fewer available resources for training, and they often fail due to fundamental and easily avoidable errors that underscore the unreliability of automatically generated code.
Abstract
Large Language Models (LLMs) are increasingly being used in everyday software engineering tasks, particularly in automated code generation. Despite their widespread adoption, these models remain far from perfect, making systematic and fair evaluation essential to understand their strengths and limitations. In the context of code generation, existing benchmarks are limited: they often target a single programming language and rely primarily on unit test outcomes, while overlooking other critical dimensions such as the overall quality of the generated code and its closeness to a valid solution. To address these gaps, we introduce PROBE, an extensible benchmark framework that, unlike prior work, establishes a systematic structure built on diverse and well-defined metrics, representative workloads, varied prompt templates, and a robust experimental procedure. In practice, the code generated by the LLMs is evaluated along three complementary dimensions: functional correctness, proximity to valid solutions, and code quality, enabling a comprehensive assessment of performance. We use PROBE to evaluate four open-source and two proprietary models under three prompting strategies across five programming languages. We further complement this analysis with a study of common errors in the code and provide concrete examples, offering clearer insight into where LLMs tend to struggle. Our findings show that, while LLMs achieve promising results, they struggle with harder problems and, in the case of smaller models, with programming languages that have fewer available resources for training, and they often fail due to fundamental and easily avoidable errors that underscore the unreliability of automatically generated code.
An automated, multi-dimensional evaluation framework for C# code generation, applying it to four state-of-the-art LLMs: GPT, Gemini, Claude, and Grok is presented and a substantial gap between correctness and quality attributes is revealed.
Seyed Mohammad Mahdi Ghalandarian, Majid Bazargani, Masoumeh Taromirad· 0 citations
It is observed that generated code often omits basic input validation or memory-safety checks, which can lead to overflows, resource exhaustion, or other reliability/security issues, and even the largest models frequently make simple mistakes.
Rodrigo Pato Nogueira, Marco Vieira, João R. Campos· 0 citations
Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question. Existing datasets and benchmarks are limited in scale, domain coverage, or executable verification, leaving the true gap between current LLMs and reliable scientific code generators inadequately assessed. To address these limitations, we present SciCodePile, the largest scientific code corpus to date, constructed from 37,737 public repositories and collectively comprising 128GB of code that spans multiple computational science disciplines. From this corpus, we further curate an executable benchmark of 200 tasks, each equipped with a sandboxed execution environment and an automated test harness for functional verification. We evaluate 15 LLMs from both open-source and closed-source families on three tasks: prefix-to-suffix completion, fill-in-the-middle infilling, and executable code generation. Results show that scientific code generation remains highly challenging: The best CodeBLEU reaches only 38.13 and 38.37 on the two completion tasks, while the strongest model achieves just 12.30\% Pass@1 on the executable benchmark, underscoring how far current models remain from reliable scientific code generation. To demonstrate the training utility of SciCodePile, we further show that continued pretraining on our corpus improves CodeBLEU by $\times$2.84 on scientific code completion, and instruction tuning on our data improves Pass@1 by $\times$4.79 on the executable benchmark. All code and data are available at https://huggingface.co/SciCodePile.
Weifeng Sun, Ye Fan, Yuchen Chen et al.· 0 citations
Large Language Models (LLMs) are predominantly assessed based on their common sense reasoning, language comprehension, and logical reasoning abilities. While models trained in specialized domains like mathematics or coding have demonstrated remarkable advancements in logical reasoning, there remains a significant gap in evaluating their code generation capabilities. Existing benchmark datasets fall short in pinpointing specific strengths and weaknesses, impeding targeted enhancements in models’ reasoning abilities to synthesize code.
To bridge this gap, this thesis introduces two novel contributions: CodeEval and CodeQual. CodeEval is an innovative, pedagogical benchmarking method that mirrors the evaluation processes encountered in academic programming courses. It comprises a multi-dimensional benchmark dataset of 602 hand-crafted problems designed to rigorously evaluate LLMs across 24 distinct aspects of Python programming, covering three proficiency levels—beginner, intermediate, and advanced—and includes both class-based and function-based problem types with detailed problem specifications and comprehensive test suites achieving 99.1% coverage. To facilitate widespread adoption, we developed RunCodeEval, an open-source execution framework that provides researchers with a ready-to-use evaluation pipeline. Our evaluation of 15 state-of-the-art LLMs revealed consistent performance degradation with increasing complexity (validated statistically, Cohen’s d = 0.790) and universal struggles with advanced concepts like concurrency.
Code quality is inherently subjective, encompassing dimensions like readability, efficiency, and adherence to language idioms that traditional static metrics fail to capture adequately. While large language models can assess these subjective qualities, lightweight models offer practical advantages: seamless CI/CD pipeline integration, lower operational costs, and full control over model behavior. We investigate whether such models can learn to assess code quality by training on synthetic LLM annotations. We introduce CodeQual, a dataset of 5,819 code samples derived from five established sources spanning diverse domains—competitive programming, pedagogical problems, software engineering, and general benchmarks—scored by LLMs across five quality dimensions, with 655 human-annotated samples for evaluation. Our fine-tuned model, CodeQualBERT, not only matches LLM performance but exceeds inter-human agreement on all five dimensions, achieving 16–100% improvement over the inter-human agreement baseline.
Together, these contributions provide a comprehensive framework for evaluating and improving LLMs in software engineering contexts, encompassing both functional correctness assessment and subjective code quality evaluation.
This tutorial introduces a reusable, end-to-end evaluation pipeline grounded in empirical software engineering practices, focusing on post-generation validation rather than prompt design, allowing for validating AI-generated code in modern development workflows.
Large language models (LLMs) have significantly advanced automatic code generation, yet most existing approaches rely on single-model inference, making their performance susceptible to model-specific limitations and failure patterns. To address this, we introduce Cross-Model Collaborative Scheduling (CMCS), a framework that enables multiple LLMs to collaboratively generate code. At its core, CMCS combines execution-guided self-correction with a peer-to-peer corrective handover mechanism, transferring unresolved problems between models to leverage their complementary strengths and mitigate the limitations of any single model. Experiments on eight code generation benchmarks show that CMCS achieves the strongest performance among the evaluated comparable-scale approaches with strong parameter efficiency. In particular, two 7B-scale models consistently outperform a much larger 30B-scale model on every benchmark where both are evaluated. When applied to proprietary models, CMCS boosts Pass@1 on APPS to 36.00%, more than three times that of the stronger individual model (11.33%). CMCS also maintains competitive accuracy when only 20% of test cases are available for diagnostic feedback. Ablation, scalability, and cost-effectiveness analyses quantify component contributions and practical deployment trade-offs. These findings indicate that cross-model collaboration offers a practical and parameter-efficient alternative to scaling up monolithic models for code generation.
Jiangping Huang, Wen-Guang Ye, Weisong Sun et al.· ACM Transactions on Software...· 0 citations