DeepSWE

DeepSWE

Agentica Project
Devstral

Devstral

Mistral AI
DeepSWE Devstral

Related Products

  • Gemini platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini platform
  • Virtuoso QA
    4.5 out of 5 stars 131 Ratings
    Visit Website for Virtuoso QA
  • Aikido Security
    4.6 out of 5 stars 367 Ratings
    Visit Website for Aikido Security
  • Flagsmith
    4.8 out of 5 stars 43 Ratings
    Visit Website for Flagsmith
  • LTX
    4.4 out of 5 stars 182 Ratings
    Visit Website for LTX
  • Splashtop Autonomous Endpoint Management
    4.7 out of 5 stars 404 Ratings
    Visit Website for Splashtop Autonomous Endpoint Management
  • Google AI Studio
    4.8 out of 5 stars 42 Ratings
    Visit Website for Google AI Studio
  • SuperOps
    4.5 out of 5 stars 297 Ratings
    Visit Website for SuperOps
  • Parasoft
    4.6 out of 5 stars 152 Ratings
    Visit Website for Parasoft
  • QA Wolf
    4.8 out of 5 stars 284 Ratings
    Visit Website for QA Wolf
DeepSWE:

About

DeepSWE is a fully open source, state-of-the-art coding agent built on top of the Qwen3-32B foundation model and trained exclusively via reinforcement learning (RL), without supervised finetuning or distillation from proprietary models. It is developed using rLLM, Agentica’s open source RL framework for language agents. DeepSWE operates as an agent; it interacts with a simulated development environment (via the R2E-Gym environment) using a suite of tools (file editor, search, shell-execution, submit/finish), enabling it to navigate codebases, edit multiple files, compile/run tests, and iteratively produce patches or complete engineering tasks. DeepSWE exhibits emergent behaviors beyond simple code generation; when presented with bugs or feature requests, the agent reasons about edge cases, seeks existing tests in the repository, proposes patches, writes extra tests for regressions, and dynamically adjusts its “thinking” effort.
Devstral:

About

Devstral is an open source, agentic large language model (LLM) developed by Mistral AI in collaboration with All Hands AI, specifically designed for software engineering tasks. It excels at navigating complex codebases, editing multiple files, and resolving real-world issues, outperforming all open source models on the SWE-Bench Verified benchmark with a score of 46.8%. Devstral is fine-tuned from Mistral-Small-3.1 and features a long context window of up to 128,000 tokens. It is optimized for local deployment on high-end hardware, such as a Mac with 32GB RAM or an Nvidia RTX 4090 GPU, and is compatible with inference frameworks like vLLM, Transformers, and Ollama. Released under the Apache 2.0 license, Devstral is available for free and can be accessed via Hugging Face, Ollama, Kaggle, Unsloth, and LM Studio.
DeepSWE:

Platforms Supported

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

Platforms Supported

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

Audience

Software engineers, researchers, and developers seeking a solution to assist with real-world coding tasks such as bug-fixing, pull-request automation, and multi-file code edits
Devstral:

Audience

Software developers and engineering teams seeking a tool to assist with code exploration, debugging, and multi-file editing tasks
DeepSWE:

Support

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

Support

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

API

Offers API Not Supported
Devstral:

API

Offers API Supported
DeepSWE:

Screenshots and Videos

Devstral:

Screenshots and Videos

DeepSWE:

Pricing

Free
Free Version Supported
Free Trial Not Supported
Devstral:

Pricing

$0.1 per million input tokens
Free Version Supported
Free Trial Not Supported
DeepSWE:

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
Devstral:

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
DeepSWE:

Training

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

Training

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

Company Information

Agentica Project
Founded: 2025
United States
agentica-project.com
Devstral:

Company Information

Mistral AI
Founded: 2023
France
mistral.ai/news/devstral
DeepSWE:

Alternatives

Devstral 2

Devstral 2

Mistral AI
Devstral:

Alternatives

DeepCoder

DeepCoder

Agentica Project
DeepSWE:
Devstral Small 2

Devstral Small 2

Mistral AI
Devstral:
DeepSWE

DeepSWE

Agentica Project
DeepSWE:
DeepCoder

DeepCoder

Agentica Project
Devstral:
Mistral Vibe

Mistral Vibe

Mistral AI
DeepSWE:
KAT-Coder-Pro V2

KAT-Coder-Pro V2

StreamLake
Devstral:
Mistral Large 3

Mistral Large 3

Mistral AI
DeepSWE:
Qwen2.5-Max

Qwen2.5-Max

Alibaba
Devstral:
Recursive Flint

Recursive Flint

Recursive
DeepSWE:

Categories

AI Coding Models Supported
AI Models Supported
Devstral:

Categories

AI Coding Models Supported
AI Models Supported
DeepSWE:

Integrations

Hugging Face Not Supported
Kaggle Not Supported
LM Studio Not Supported
Mistral AI Not Supported
Mistral Code Not Supported
Ollama Not Supported
Together AI Supported
Unsloth Not Supported
Devstral:

Integrations

Hugging Face Supported
Kaggle Supported
LM Studio Supported
Mistral AI Supported
Mistral Code Supported
Ollama Supported
Together AI Not Supported
Unsloth Supported
DeepSWE:
Claim DeepSWE and update features and information
Claim DeepSWE and update features and information
Devstral:
Claim Devstral and update features and information
Claim Devstral and update features and information