Cline v3.41 adds GPT-5.2, Devstral 2, & ergonomic model switching
GPT-5.2 brings frontier-level agentic performance. Devstral 2 is the best open-weights option for Cline. And the new model picker makes switching between them instant.
Devstral 2: The best open-weights model for Cline just dropped
The stealth model is finally public: Devstral 2 scores 72.2% on SWE-bench Verified and works smoothly with Cline's multi-step tool workflows. Free for a limited time!
Cline v3.39 introduces Explain Changes: understand AI-generated code before you ship it
Understand AI-generated code before you ship it
Free stealth model "microwave" now available in Cline
A new agentic coding model built for Cline drops today with free access during alpha.
DeepSeek V3.2 and V3.2-Speciale are now available in Cline
DeepSeek's new reasoning-first models are live. V3.2 for daily agentic coding; V3.2-Speciale for maximum reasoning power. Both at $0.28/$0.42 per million tokens.
Anthropic's Claude Opus 4.5 is Live in Cline
Opus 4.5 is Anthropic's most capable model. Use it for complex multi-step problems, heavy MCP usage, and tasks requiring autonomous reasoning through ambiguity.
Introducing cline-bench: A Real-World, Open Source Benchmark for Agentic Coding
A call for contribution to establish reproducible, practical reinforcement learning environments sourced from real open source development work — with a $1M commitment to support open source maintainers.
Gemini 3 Pro gives Cline more headroom for long-running coding
Gemini 3 Pro extends what Cline can attempt as an autonomous coding agent while keeping you in control.
Cline 3.38.0: Gemini 3 Pro Preview & Voice Dictations that understands your code
Cline 3.38.0 introduces Gemini 3 Pro Preview for enhanced reasoning and multimodal capabilities. We've also added AquaVoice Avalon, a voice-to-text model that specifically understands technical terms
OpenAI's GPT-5.1 is an obsessive researcher, and Cline gives it focus
After weeks with GPT-5.1, we discovered it's unlike any coding model we've seen. It investigates obsessively, follows structure religiously, and sustains focus across massive tasks. We adapted Cline to channel these traits into stable, long-running execution.
Cline 3.37: GPT-5.1, Nous Research Models, and Avalon Speech-to-Text
GPT-5.1 ships with Cline-optimized prompting. Plus Nous Research's Hermes 4 models, Avalon speech-to-text with Linux support, and critical bug fixes.
Cline v3.36: Hooks - Inject Custom Logic Into Cline's Workflow
Hooks let you inject custom scripts at key workflow moments to validate operations, monitor usage, and shape AI decisions. Currently supported on macOS and Linux.