Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Das, Gunjan, Bhattacharya, Paheli, Gupta, Rishabh
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.04673
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911301896241152
author Das, Gunjan
Bhattacharya, Paheli
Gupta, Rishabh
author_facet Das, Gunjan
Bhattacharya, Paheli
Gupta, Rishabh
contents Large Language Models (LLMs) have revolutionized both general natural language processing and domain-specific applications such as code synthesis, legal reasoning, and finance. However, while prior studies have explored individual model capabilities, a systematic cross-domain comparison that unifies linguistic, reasoning, and code understanding abilities remains underexplored. In this work, we present a comprehensive evaluation of five general-purpose and three code-specific state-of-the-art LLMs across six diverse benchmarks encompassing linguistic competence, mathematical reasoning, and trustworthiness. Additionally, we analyze model behavior on the CoNaLa dataset for code explanation, comparing natural language and code-specialized LLMs. Our findings reveal that models optimized for code (e.g., CodeLLaMA variants) exhibit strong reasoning and syntactic precision, that even for non-coding tasks can show measurable performance gains, in contrast to general-purpose models like Mistral-7B and Llama-3-8B.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04673
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-Task Benchmarking and Evaluation of General-Purpose and Code-Specific Large Language Models
Das, Gunjan
Bhattacharya, Paheli
Gupta, Rishabh
Software Engineering
Large Language Models (LLMs) have revolutionized both general natural language processing and domain-specific applications such as code synthesis, legal reasoning, and finance. However, while prior studies have explored individual model capabilities, a systematic cross-domain comparison that unifies linguistic, reasoning, and code understanding abilities remains underexplored. In this work, we present a comprehensive evaluation of five general-purpose and three code-specific state-of-the-art LLMs across six diverse benchmarks encompassing linguistic competence, mathematical reasoning, and trustworthiness. Additionally, we analyze model behavior on the CoNaLa dataset for code explanation, comparing natural language and code-specialized LLMs. Our findings reveal that models optimized for code (e.g., CodeLLaMA variants) exhibit strong reasoning and syntactic precision, that even for non-coding tasks can show measurable performance gains, in contrast to general-purpose models like Mistral-7B and Llama-3-8B.
title Cross-Task Benchmarking and Evaluation of General-Purpose and Code-Specific Large Language Models
topic Software Engineering
url https://arxiv.org/abs/2512.04673