MétaCan
Menu
Back to cohort
Record W4412438306 · doi:10.1145/3730436.3730529

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

2025· article· en· W4412438306 on OpenAlexaff
Yanxin Shen, Lun Wang, Chuanqi Shi, Shaoshuai Du, Yiyi Tao, Yixian Shen

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsSimon Fraser University
Fundersnot available
KeywordsComputer scienceContext (archaeology)Code (set theory)Programming languageNatural language processing

Abstract

fetched live from OpenAlex

Large language models (LLMs) have transformed code completion and made it a more intelligent, context-aware tool in contemporary integrated development systems. These developments have greatly improved developers' capacity for error-free, effective code writing. Using the Syntax-Aware Fill-in- the- Middle (SAFIM) dataset, this work assesses different chat-based LLMs, including Gemini 1.5 Flash, Gemini 1.5 Pro, GPT-4o, GPT-4o-mini, and GPT-4 Turbo. This benchmark is intended especially to evaluate models' syntactic sensitivity in code creation. Accuracy and efficiency were assessed using performance benchmarks including cosine similarity with ground-truth complements and latency. The results expose significant variations in the code completion skills of the models, therefore providing insightful analysis of their distinct strengths and shortcomings. This paper offers a baseline for next developments in LLM-based code completion by means of a comparative study stressing the trade-offs between correctness and speed.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.021
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.020
Threshold uncertainty score0.039

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.021
Meta-epidemiology (narrow)0.0020.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0030.002
Science and technology studies0.0010.001
Scholarly communication0.0020.002
Open science0.0020.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0020.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.077
GPT teacher head0.376
Teacher spread0.300 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207