Saved in:
Bibliographic Details
Main Authors: Xing, Jun, Bhatia, Mayur, Phulwani, Sahil, Suresh, Darshan, Matta, Rafik
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.00226
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915132568764416
author Xing, Jun
Bhatia, Mayur
Phulwani, Sahil
Suresh, Darshan
Matta, Rafik
author_facet Xing, Jun
Bhatia, Mayur
Phulwani, Sahil
Suresh, Darshan
Matta, Rafik
contents Evaluating the real-world applicability of large language models (LLMs) provides valuable insights for their development and use in software development tasks. Existing benchmarks often focus on standalone coding problems or specific libraries, overlooking multi-file, project-based scenarios and lacking a rigorous evaluation of consistency. The HackerRank-ASTRA Benchmark introduces project-based coding problems that mirror real-world scenarios. It evaluates model consistency through 32 runs (k = 32) and median standard deviation while incorporating taxonomy-level analysis to assess sub-skill capabilities. Initial evaluations on 65 problems show that the top three models -- o1, o1-preview, and Claude-3.5-Sonnet-1022 -- achieved comparable average scores of 75%, with no statistically significant differences in performance. Notably, Claude-3.5-Sonnet-1022 demonstrated the highest consistency across problems, with low variability (SD = 0.0497), which was statistically significant compared to other models, highlighting its reliability for real-world software development tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00226
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HackerRank-ASTRA: Evaluating Correctness & Consistency of Large Language Models on cross-domain multi-file project problems
Xing, Jun
Bhatia, Mayur
Phulwani, Sahil
Suresh, Darshan
Matta, Rafik
Machine Learning
Software Engineering
Evaluating the real-world applicability of large language models (LLMs) provides valuable insights for their development and use in software development tasks. Existing benchmarks often focus on standalone coding problems or specific libraries, overlooking multi-file, project-based scenarios and lacking a rigorous evaluation of consistency. The HackerRank-ASTRA Benchmark introduces project-based coding problems that mirror real-world scenarios. It evaluates model consistency through 32 runs (k = 32) and median standard deviation while incorporating taxonomy-level analysis to assess sub-skill capabilities. Initial evaluations on 65 problems show that the top three models -- o1, o1-preview, and Claude-3.5-Sonnet-1022 -- achieved comparable average scores of 75%, with no statistically significant differences in performance. Notably, Claude-3.5-Sonnet-1022 demonstrated the highest consistency across problems, with low variability (SD = 0.0497), which was statistically significant compared to other models, highlighting its reliability for real-world software development tasks.
title HackerRank-ASTRA: Evaluating Correctness & Consistency of Large Language Models on cross-domain multi-file project problems
topic Machine Learning
Software Engineering
url https://arxiv.org/abs/2502.00226