GLM-5

GLM-5

Z.ai
SWE-2

SWE-2

Cognition
+
+

Related Products

  • Gemini Enterprise Agent Platform
    999 Ratings
    Visit Website
  • Google AI Studio
    30 Ratings
    Visit Website
  • Concord
    237 Ratings
    Visit Website
  • Planview AdaptiveWork
    714 Ratings
    Visit Website
  • Teradata VantageCloud
    1,121 Ratings
    Visit Website
  • ONLYOFFICE Docs
    715 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Interfacing Integrated Management System (IMS)
    66 Ratings
    Visit Website
  • Evertune
    1 Rating
    Visit Website
  • JS7 JobScheduler
    1 Rating
    Visit Website

About

GLM-5 is Z.ai’s latest large language model built for complex systems engineering and long-horizon agentic tasks. It scales significantly beyond GLM-4.5, increasing total parameters and training data while integrating DeepSeek Sparse Attention to reduce deployment costs without sacrificing long-context capacity. The model combines enhanced pre-training with a new asynchronous reinforcement learning infrastructure called slime, improving training efficiency and post-training refinement. GLM-5 achieves best-in-class performance among open-source models across reasoning, coding, and agent benchmarks, narrowing the gap with leading frontier models. It ranks highly on evaluations such as Vending Bench 2, demonstrating strong long-term planning and operational capabilities. The model is open-sourced under the MIT License.

About

SWE-2 is Cognition’s advanced coding model designed to improve software engineering performance while reducing the cost of agentic coding workflows. The model is post-trained from Kimi K3 and uses reinforcement learning to optimize multiple reasoning-effort levels within a single training run. SWE-2 is designed to explore codebases more selectively, begin implementation sooner, and complete tasks with fewer redundant reads and reasoning steps than earlier Cognition models. Its capabilities include code generation, debugging, test creation, verification, repository analysis, and complex terminal-based software engineering tasks. The model also emphasizes stronger engineering judgment, end-to-end test coverage, instruction following, and evidence-based verification of user assumptions. SWE-2 is available through Devin Desktop and Devin CLI, with broader rollout planned across Devin Web and Fusion.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

AI researchers, developers, and engineering teams seeking an open-source, high-performance foundation model for advanced reasoning, coding, and long-horizon agentic applications

Audience

Software developers, engineering teams, AI coding agent users, DevOps professionals, and organizations that need capable agentic software engineering with lower execution cost and more efficient reasoning

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Open source
Free Version
Free Trial

Pricing

$20/month
Free Version
Free Trial

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 5.0 / 5
ease 5.0 / 5
features 5.0 / 5
design 5.0 / 5

Pros & Cons from Real Users

Pros

  • The biggest thing that stands out is the cost-performance balance. SWE-2 is not just trying to top one benchmark; it is trying to get very close to frontier coding performance at a much lower cost. For developers, that matters a lot. Coding agents can burn through tokens quickly when they are reading files, making edits, running tests, and iterating. A model that performs near the top while being meaningfully cheaper is much easier to use every day. I also like that SWE-2 seems built for real software engineering workflows, not just isolated code snippets. The strong DeepSWE and Terminal-Bench results make it especially interesting for repo-level tasks, debugging, tool use, and longer agent runs.

Cons

  • Benchmarks are useful, but real projects bring messy architecture, flaky tests, undocumented behavior, and weird edge cases.

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Z.ai
Founded: 2023
China
z.ai/

Company Information

Cognition
Founded: 2023
United States
cognition.com

Alternatives

Alternatives

Claude Opus 4.5

Claude Opus 4.5

Anthropic
Claude Opus 4.6

Claude Opus 4.6

Anthropic
GPT-5.6 Sol

GPT-5.6 Sol

OpenAI
GLM-5.3

GLM-5.3

Z.ai
SWE-1.7

SWE-1.7

Cognition
ERNIE 5.1

ERNIE 5.1

Baidu
SWE-1.6

SWE-1.6

Cognition

Categories

Categories

Integrations

APIFree
Cerebras
Cheaper Inference
Dessix
Devin
HTML
JSON
JavaScript
Lua
OpenRouter
Oxlo.ai
Python
Qoder
Rust
Solidity
Sup AI
Swift
TypeScript
XML
Yonoo

Integrations

APIFree
Cerebras
Cheaper Inference
Dessix
Devin
HTML
JSON
JavaScript
Lua
OpenRouter
Oxlo.ai
Python
Qoder
Rust
Solidity
Sup AI
Swift
TypeScript
XML
Yonoo
Claim GLM-5 and update features and information
Claim GLM-5 and update features and information
Claim SWE-2 and update features and information
Claim SWE-2 and update features and information