Comparative Analysis of Large Language Models for Context-Aware Code Completion using SAFIM Framework

TL;DR

This paper compares the performance of various large language models in syntax-aware code completion using the SAFIM benchmark, highlighting differences in accuracy and efficiency to guide future development.

Contribution

It introduces a comprehensive benchmark for evaluating LLMs in syntax-sensitive code completion and provides a detailed comparative analysis of multiple models.

Findings

Significant performance differences among models.

Trade-offs between accuracy and latency.

Benchmark establishes a standard for future research.

Abstract

The advent of Large Language Models (LLMs) has revolutionized code completion, transforming it into a more intelligent and context-aware feature in modern integrated development environments. These advancements have significantly enhanced developers' ability to write efficient and error-free code. This study evaluates the performance of several chat-based LLMs, including Gemini 1.5 Flash, Gemini 1.5 Pro, GPT-4o, GPT-4o-mini, and GPT-4 Turbo, using the Syntax-Aware Fill-in-the-Middle (SAFIM) dataset. This benchmark is specifically designed to assess models' capabilities in syntax-sensitive code generation. Performance metrics, such as cosine similarity with ground-truth completions and latency, were employed to measure both accuracy and efficiency. The findings reveal substantial differences in the models' code completion abilities, offering valuable insights into their respective strengths and weaknesses. This work provides a comparative analysis that underscores the trade-offs between accuracy and speed, establishing a benchmark for future advancements in LLM-based code completion.