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…

IDE plugins · Continuity · Jan 19–25, 2026

2 releases · updated

plugins add GPT-5.2-Codex and Agent Skills

Two releases of plugins shipped this week, bringing improvements to the product and new models, which will help developers working with large codebases. The main change is the addition of GPT-5.2-Codex and Agent Skills. These updates are particularly useful for developers using Cascade and Windsurf.

v2.12.5 · January 25, 2026

Also shipped to the Next channel as v2.13.5.

This release is fixes only, with the most notable fix being the resolution of the Cascade crash on Windows caused by connection errors.

Official release notes

Bug Fixes

2.12.5 changelog banner

Bug Fixes

  • Fixed Cascade crash on Windows caused by “site can’t be reached” connection errors.

v2.12.4 · January 23, 2026

Also shipped to the Next channel as v2.13.4.

This release adds support for GPT-5.2-Codex and introduces Agent Skills for Cascade. It also includes several patch fixes, such as resolving issues with the Cascade panel and language server process. Additionally, a new hook for initializing worktrees in Cascade has been added.

Official release notes

Product Improvements & New Models ✨

2.12.4 changelog banner

GPT-5.2-Codex

  • Adds support for GPT-5.2-Codex with four reasoning efforts (low, medium, high, and xhigh).
  • GPT-5.2-Codex is OpenAI’s latest model designed for agentic coding.
  • It excels at working in large codebases over long sessions.
  • For most tasks, we recommend using the medium reasoning effort.

Agent Skills

Patch Fixes

  • Fixed Cascade panel occasionally going blank during idle periods.
  • Fixed language server process not terminating when IDE is closed.
  • Fixed keyboard shortcuts on Rider.
  • Added post_setup_worktree hook for initializing worktrees in Cascade

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