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 9) — 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 Desktop: Continuity — 2026-10-25 Devin Desktop Update — 2026-10-24 BlackRock adopts Devin Plugins to govern AI agents at enterprise scale Cognizant and Cognition report 37% cost saving from Devin-powered AI e… Devin adds Microsoft Teams and 365 integrations Factory AI CEO accuses former board adviser of spying for rival Cognit… GPT-6.1 Sol added to Devin Desktop and CLI Devin Desktop: Continuity — 2026-10-23 PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 9) — 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 Desktop: Continuity — 2026-10-25 Devin Desktop Update — 2026-10-24 BlackRock adopts Devin Plugins to govern AI agents at enterprise scale Cognizant and Cognition report 37% cost saving from Devin-powered AI e… Devin adds Microsoft Teams and 365 integrations Factory AI CEO accuses former board adviser of spying for rival Cognit… GPT-6.1 Sol added to Devin Desktop and CLI Devin Desktop: Continuity — 2026-10-23

Releases · News

Devin CLI v3000.3.22: Smarter Permissions and Plugins

Devin CLI version 3000.3.22 shipped recently, bringing a new smart permission mode that auto-approves routine development work, such as building, testing, and linting. This mode also allows for faster model-based decisions on other actions, like shell commands and fetches.

What shipped

  • New smart permission mode for auto-approving routine dev work and faster model-based decisions
  • Plugins can now contribute rules, hooks, MCP servers, and custom subagents
  • New plugin sources and manifest options, including git-subdir and Claude-compatible manifests
  • Editable command approvals and global “Yes, always allow” options for commands and web fetches
  • Configurable keybindings and automatic discovery of Copilot agent skills

Sources