DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909050980007936 |
|---|---|
| author | Kumarappan, Adarsh Golnari, Pareesa Ameneh Wen, Wen Liu, Xiaoyu Ryan, Gabriel Sun, Yuting Fu, Shengyu Nallipogu, Elsie |
| author_facet | Kumarappan, Adarsh Golnari, Pareesa Ameneh Wen, Wen Liu, Xiaoyu Ryan, Gabriel Sun, Yuting Fu, Shengyu Nallipogu, Elsie |
| contents | DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,800 evaluation instances across six programming languages and six task categories derived from real developer telemetry and synthesized using generator models from multiple provider families to mitigate single-source bias. Unlike prior benchmarks, it emphasizes ecological validity, avoids training data contamination, and enables detailed diagnostics. The evaluation combines functional correctness, similarity-based metrics, and LLM-judge assessments focused on usefulness and contextual relevance. 9 state-of-the-art models were assessed, with the strongest achieving only 43.5% Pass@1, confirming the benchmark remains challenging and revealing differences in syntactic precision, semantic reasoning, and practical utility. Our benchmark provides actionable insights to guide model selection and improvement, detail that is often missing from other benchmarks but is essential for both practical deployment and targeted model development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11895 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models Kumarappan, Adarsh Golnari, Pareesa Ameneh Wen, Wen Liu, Xiaoyu Ryan, Gabriel Sun, Yuting Fu, Shengyu Nallipogu, Elsie Machine Learning Artificial Intelligence Software Engineering DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,800 evaluation instances across six programming languages and six task categories derived from real developer telemetry and synthesized using generator models from multiple provider families to mitigate single-source bias. Unlike prior benchmarks, it emphasizes ecological validity, avoids training data contamination, and enables detailed diagnostics. The evaluation combines functional correctness, similarity-based metrics, and LLM-judge assessments focused on usefulness and contextual relevance. 9 state-of-the-art models were assessed, with the strongest achieving only 43.5% Pass@1, confirming the benchmark remains challenging and revealing differences in syntactic precision, semantic reasoning, and practical utility. Our benchmark provides actionable insights to guide model selection and improvement, detail that is often missing from other benchmarks but is essential for both practical deployment and targeted model development. |
| title | DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models |
| topic | Machine Learning Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2601.11895 |