CodeT5

CodeT5

Salesforce
+
+

Related Products

  • Google Cloud Run
    349 Ratings
    Visit Website
  • Docmosis
    51 Ratings
    Visit Website
  • Checksum.ai
    2 Ratings
    Visit Website
  • Google Cloud BigQuery
    2,027 Ratings
    Visit Website
  • Google AI Studio
    41 Ratings
    Visit Website
  • XpertCoding
    42 Ratings
    Visit Website
  • Planview AdaptiveWork
    718 Ratings
    Visit Website
  • Rocket z/Assure VAP
    1 Rating
    Visit Website
  • LTX
    182 Ratings
    Visit Website
  • Source Defense
    7 Ratings
    Visit Website

About

Code for CodeT5, a new code-aware pre-trained encoder-decoder model. Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. This is the official PyTorch implementation for the EMNLP 2021 paper from Salesforce Research. CodeT5-large-ntp-py is specially optimized for Python code generation tasks and employed as the foundation model for our CodeRL, yielding new SOTA results on the APPS Python competition-level program synthesis benchmark. This repo provides the code for reproducing the experiments in CodeT5. CodeT5 is a new pre-trained encoder-decoder model for programming languages, which is pre-trained on 8.35M functions in 8 programming languages (Python, Java, JavaScript, PHP, Ruby, Go, C, and C#). In total, it achieves state-of-the-art results on 14 sub-tasks in a code intelligence benchmark - CodeXGLUE. Generate code based on the natural language description.

About

Qwen3‑Coder is an agentic code model available in multiple sizes, led by the 480B‑parameter Mixture‑of‑Experts variant (35B active) that natively supports 256K‑token contexts (extendable to 1M) and achieves state‑of‑the‑art results on Agentic Coding, Browser‑Use, and Tool‑Use tasks comparable to Claude Sonnet 4. Pre‑training on 7.5T tokens (70 % code) and synthetic data cleaned via Qwen2.5‑Coder optimized both coding proficiency and general abilities, while post‑training employs large‑scale, execution‑driven reinforcement learning and long‑horizon RL across 20,000 parallel environments to excel on multi‑turn software‑engineering benchmarks like SWE‑Bench Verified without test‑time scaling. Alongside the model, the open source Qwen Code CLI (forked from Gemini Code) unleashes Qwen3‑Coder in agentic workflows with customized prompts, function calling protocols, and seamless integration with Node.js, OpenAI SDKs, and more.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Supported
Mac Supported
Linux Supported
Cloud Not Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

Developers and users interested in a solution to generate, summarize, and autocomplete code

Audience

AI researchers and software engineers interested in a tool providing an agentic coding model with large‑context support and turnkey CLI tools for real‑world, and automated code generation

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Not Supported

API

Offers API Not Supported

Screenshots and Videos

Screenshots and Videos

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Pricing

Free
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Supported
In Person Not Supported

Company Information

Salesforce
github.com/salesforce/CodeT5

Company Information

Qwen
Founded: 2023
China
github.com/QwenLM/qwen-code

Alternatives

GLM-OCR

GLM-OCR

Z.ai

Alternatives

Mu

Mu

Microsoft
MiMo Code

MiMo Code

Xiaomi Technology
CodeQwen

CodeQwen

Alibaba

Categories

AI Code Generators Supported

Categories

Agentic AI Supported
AI Coding Agents Supported

Integrations

Alibaba AI Coding Plan Not Supported
C Supported
C# Supported
Claude Fable 5.1 Not Supported
Claude Mythos 5 Not Supported
Claude Opus 4.5 Not Supported
Claude Opus 4.7 Not Supported
Claude Opus 4.8 Not Supported
Claude Opus 5 Not Supported
Claude Sonnet 4.5 Not Supported
Claude Sonnet 4.6 Not Supported
Melaya Not Supported
PHP Supported
Python Supported
Qwen 4 Not Supported
Qwen2.5 Not Supported
Qwen3.8-Flash-Next Not Supported
Qwen3.8-Omni-Flash Not Supported
Step 5 Preview Not Supported
SuperBased Not Supported

Integrations

Alibaba AI Coding Plan Supported
C Not Supported
C# Not Supported
Claude Fable 5.1 Supported
Claude Mythos 5 Supported
Claude Opus 4.5 Supported
Claude Opus 4.7 Supported
Claude Opus 4.8 Supported
Claude Opus 5 Supported
Claude Sonnet 4.5 Supported
Claude Sonnet 4.6 Supported
Melaya Supported
PHP Not Supported
Python Not Supported
Qwen 4 Supported
Qwen2.5 Supported
Qwen3.8-Flash-Next Supported
Qwen3.8-Omni-Flash Supported
Step 5 Preview Supported
SuperBased Supported
Claim CodeT5 and update features and information
Claim CodeT5 and update features and information
Claim Qwen Code and update features and information
Claim Qwen Code and update features and information