REVIEW 9 cited by
Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibility
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibility
read the original abstract
Code-related benchmarks play a critical role in evaluating large language models (LLMs), yet their quality fundamentally shapes how the community interprets model capabilities. In the past few years, awareness of benchmark quality has grown. Yet, after a decade-scale (2014-2025) survey over 672 code benchmarks, we observed a lag between growing awareness and actual practice. For example, in 2025 alone, the number of benchmarks that ignore code coverage when providing test cases nearly matches the total count accumulated across the previous ten years. In response, we take a clear position: Code benchmarks must prioritize rigor in benchmark construction, reliability in evaluation, and reproducibility in release. To operationalize this position, we introduce a code benchmark guideline HOW2BENCH with 55 checklists. Finally, our further human study also exposed that the current issues not only stem from the significant effort required, but also from a lack of awareness regarding their importance.
Forward citations
Cited by 9 Pith papers
-
Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks
The two main benchmarks for LLM instructed code editing over-represent Python, miss common real-world domains and edit types, and have test coverage issues that limit what they measure.
-
AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation
AlgoBench creates traceable variants of competitive programming problems via constraint shifts that invalidate original algorithms, paired with complexity metrics that reveal LLMs often produce functionally correct bu...
-
Flaws in the LLM Automation Narrative
A new code-writing data analysis benchmark shows human experts outperforming a frontier LLM on average with lower performance variance.
-
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
-
To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
Even test-passing LLM patches keep code developers deleted; a 200-task deletion-only benchmark and 0.7% post-training data show the behavior is measurable and learnable.
-
Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study
APIKG4Syn synthesizes API-oriented training data via knowledge graphs and Monte Carlo search to fine-tune a 7B model that reaches 25% pass@1 on HarmonyOS code generation, beating untuned GPT-4o at 17.59%.
-
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
A group of 22 researchers proposes seven study types and eight guidelines for empirical software engineering studies involving LLMs to enhance reproducibility and replicability.
-
Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models
MedCheck is a lifecycle checklist framework that audits 53 existing medical LLM benchmarks and identifies systemic gaps in clinical fidelity, contamination control, and safety metrics.
-
Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation
Cross-lingual RACG shows non-trivial but unequal knowledge transfer across 13 programming languages, depending on linguistic affinity and pretraining diversity, with limited reliance on natural language information wh...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.