Skip to content
Models
PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin launches Devin Apps, private web tools hosted on its cloud compu… Devin adds free SWE‑2 sessions and desktop access to Teams plan Gemini 4 Hydrogen launches in Devin Desktop and CLI, matching GPT‑6.1 … Basis reduces 20‑hour accounting process to 30 minutes with Devin Clou… Claude Mythos 5.2 added to Devin Security with benchmark score of 73.5 Gemini 4 Carbon added to Devin Desktop and CLI, scores 40% on Frontier… Claude Fable 5.2 added to Devin, leads FrontierCode 2.0 benchmark with… Devin offers 50% off Teams plan for users migrating from competing cod… PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin launches Devin Apps, private web tools hosted on its cloud compu… Devin adds free SWE‑2 sessions and desktop access to Teams plan Gemini 4 Hydrogen launches in Devin Desktop and CLI, matching GPT‑6.1 … Basis reduces 20‑hour accounting process to 30 minutes with Devin Clou… Claude Mythos 5.2 added to Devin Security with benchmark score of 73.5 Gemini 4 Carbon added to Devin Desktop and CLI, scores 40% on Frontier… Claude Fable 5.2 added to Devin, leads FrontierCode 2.0 benchmark with… Devin offers 50% off Teams plan for users migrating from competing cod…

Devin Desktop · Continuity · Nov 10–16, 2025

4 releases · updated

Devin Desktop: Worktree Preview

Devin Desktop shipped four releases this week, with the main change being the addition of Worktree Preview, which helps developers explore and modify code across multiple branches simultaneously. This feature is part of the larger effort to improve the overall coding experience. The releases also included various fixes and improvements to existing features.

v1.12.150 (Next) · November 14, 2025

Release v1.12.150 includes Worktree Preview, which allows using Windsurf’s AI agent with worktrees to explore and modify code across multiple branches simultaneously. It also includes MCP Server Improvements, which fix issues with scopes and OAuth authentication flows for multiple MCP servers, and improved Tab Completion with better latency, responsiveness, and accuracy. Additionally, a Context Window Indicator Beta is introduced to show the current context window used by the Cascade AI agent.

Official release notes

Worktree Preview

You can now use Windsurf’s AI agent with worktrees to explore and modify code across multiple branches simultaneously.

MCP Server Improvements

  • Fixes issues with scopes and OAuth authentication flows for multiple MCP servers

Tab Completion

  • Improved latency, responsiveness, and accuracy of autocomplete.

Context Window Indicator Beta

  • Context window indicator now shows the current context window used by the Cascade AI agent.

v1.12.32 · November 14, 2025

Also shipped to the Next channel as v1.12.149.

Release v1.12.32 adds priority processing support for GPT-5.1 models, providing guaranteed low-latency responses for faster AI assistance. It also includes a fix for tool call calling issues for GPT-5.1-Codex and GPT-5.1-Codex Mini models.

Official release notes

GPT-5.1 Priority Mode

  • Added priority processing support for GPT-5.1 models, providing guaranteed low-latency responses for faster (~50 tokens/sec), more reliable AI assistance.
  • Priority processing costs 2x the standard rate, which will be reflected in the Windsurf credit system.

Patch Fixes and Improvements

  • Fixed tool call calling issues for GPT-5.1-Codex and GPT-5.1-Codex Mini models

v1.12.148 (Next) · November 13, 2025

Release v1.12.148 introduces GPT-5.1 and GPT-5.1-Codex models in Windsurf, which deliver a solid upgrade from GPT-5 for agentic coding workflows. The release also includes a new shortcut to attach the current file to Cascade and fixes an issue with PowerShell and Turbo Mode. The Knowledge Base feature is removed in this release.

Official release notes

GPT-5.1 and GPT-5.1-Codex

1.12.148 GPT-5.1 and GPT-5.1-Codex changelog banner

GPT-5.1 and GPT-5.1-Codex are now available in Windsurf. GPT-5.1 will become the default model in Windsurf for one week, and paid users get free access during this period.

GPT-5.1 and GPT-5.1-Codex deliver a solid upgrade from GPT-5 for agentic coding workflows. They’re noticeably better at understanding what you’re asking for and working with you to get it done. The new variable thinking feature dynamically adjusts reasoning depth—providing quick responses for simple tasks and more thoughtful analysis when complexity demands it.

Patch Fixes and Improvements

Removed Features

  • Knowledge Base: Removed the Knowledge Base feature

Bug Fixes

  • PowerShell + Turbo Mode: Fixed an issue where PowerShell was not running commands when Turbo Mode is enabled

Shortcuts

  • Attach current file to Cascade: New shortcut Option/Alt+Cmd+L when in an editor to attach the current file to Cascade

v1.12.31 · November 13, 2025

Release v1.12.31 also introduces GPT-5.1 and GPT-5.1-Codex models in Windsurf, with the same improvements as v1.12.148. It also includes MCP Improvements, such as loading state indicators and refresh only edited MCPs, as well as the new Cascade Hooks feature and SWE 1.5 image support. The Knowledge Base feature is removed in this release, and several bug fixes are included, such as fixing Vim extension typing lag and PowerShell issues with Turbo Mode.

Official release notes

GPT-5.1 and GPT-5.1-Codex

1.12.31 GPT-5.1 and GPT-5.1-Codex changelog banner

GPT-5.1 and GPT-5.1-Codex are now available in Windsurf. GPT-5.1 will become the default model in Windsurf for one week, and paid users get free access during this period.

GPT-5.1 and GPT-5.1-Codex deliver a solid upgrade from GPT-5 for agentic coding workflows. They’re noticeably better at understanding what you’re asking for and working with you to get it done. The new variable thinking feature dynamically adjusts reasoning depth—providing quick responses for simple tasks and more thoughtful analysis when complexity demands it.

Patch Fixes and Improvements

MCP Improvements

  • Loading state indicators: Show loading state per installed MCP to improve visibility during initialization.
  • Refresh only edited MCPs: When mcp_config.json is modified, only the affected MCP server instance is initialized/refreshed; no other instances are refreshed.
  • Increased initialization timeout: MCP initialization timeout increased to 60s.
  • Refresh button for error states: Show refresh button for MCPs in error state to allow manual recovery.

Cascade Hooks

  • Cascade Hooks feature: New Cascade Hooks feature available to all tiers.
  • Documentation: See Cascade Hooks docs for available hooks and usage examples.

SWE 1.5 Image Support

  • Image understanding: SWE 1.5 now supports image understanding, enabling visual content analysis.

Removed Features

  • Knowledge Base: Removed the Knowledge Base feature.

Bug Fixes

  • Vim extension typing lag: Fixed bug causing typing lag when Vim extension is enabled.
  • PowerShell + Turbo Mode: Fixed an issue where PowerShell was not running commands when Turbo Mode is enabled.

Shortcuts

  • Attach current file to Cascade: New shortcut Option/Alt+Cmd+L when in an editor to attach the current file to Cascade.

Fan coverage from Devin Central — not an official Cognition announcement. Devin is a trademark of Cognition.