4dand/1c-ai-codegen-research-paper
Научная работа «Экспериментальная оценка эффективности искусственного интеллекта в генерации кода для доменно-специфичных платформ (на примере 1С:Предприятие 8)». SMOP-метрика, эксперименты с LLM, платформа GenLab-1C. НДР-2026.
This research evaluates how effectively large language models (LLMs) can generate code for the 1C:Enterprise 8 platform using its built-in BSL language. It analyzes what goes into the models (problem descriptions, platform metadata) and what comes out (BSL code), providing a quality score. This information is valuable for 1C developers and project managers interested in using AI for code generation.
Use this if you are an 1C developer or project manager considering using AI for generating BSL code and want to understand the current capabilities and limitations of different LLMs for both general algorithms and platform-specific tasks.
Not ideal if you are looking for a ready-to-use AI code generation tool for 1C, as this is a research paper evaluating model performance, not a product.
Stars
11
Forks
1
Language
1C Enterprise
License
—
Category
Last pushed
Apr 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/4dand/1c-ai-codegen-research-paper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Dav1dde/glad
Multi-Language Vulkan/GL/GLES/EGL/GLX/WGL Loader-Generator based on the official specs.
Aleph-Alpha/ts-rs
Generate TypeScript bindings from Rust types
apollographql/apollo-tooling
✏️ Apollo CLI for client tooling (Mostly replaced by Rover)
mmcloughlin/avo
Generate x86 Assembly with Go
krzysztofzablocki/Sourcery
Meta-programming for Swift, stop writing boilerplate code.