DeepSeek V4.1-Flash-1017 has released, beating GPT 5.6 Sol on Terminal-Bench while being ~17x cheaper. It improves the previous DeepSeek V4.1-Flash result by 35%, accomplished with "no algorithmic innovation" but instead by RL training it on multiple coding agent harnesses.

Cline Desktop now runs in the cloud! ☁️ Run multiple tasks in parallel - each in its own secure cloud sandbox - and close your laptop while Cline keeps working.

Gemini 4 Argon had the best launch day user share of any frontier model on Cline since June. ~3x as many users tried it on day one as Claude Opus 5.5 or Sonnet 5.5. We're also seeing Argon using 30% fewer tokens on average than Claude models. It's a really efficient model!

Gemini 4 Argon is #1 on Val Index, completing agentic tasks at half the cost of Opus 5.5. Google shared that the Chrome team recently used Argon to refactor ~6 million lines of legacy features out of a 40-million line codebase, eliminating an entire category of browser crashes.

Meta’s Muse Wonder now leads on DeepSWE. This is an incredible turnaround only 14 months after the announcement of Meta Superintelligence Labs. We have a new model on the frontier.

Step 5 Preview is now free in Cline. On DeepSWE it scores ahead of Kimi K3 and GLM-5.3, making it one of the strongest open weights coding models available.

1/ Introducing Cline Cloud Agents. You can now use Cline straight from your browser. Give it a task and it runs in a secure cloud sandbox, writing code, testing its work, then opening a PR on your GitHub repo.

Mistral Large 4 beats Opus 5.5 and GPT-6 Astra on cybersecurity benchmarks, largely because it refuses far fewer security tasks. Meanwhile Opus and Astra had ~40% of tasks blocked by their own safety filters.

Pareto 26.10 Preview is a new model available in Cline. It routes to several frontier and open models, grades the answer, & returns the best one - while preserving prompt cache + keeping cost low. ~56x cheaper than Fable for the same DeepSWE score at $0.24 per task vs $13.41!

1/ Cline Desktop now has Connectors (beta). Connect Gmail, Slack, Google Calendar, Linear, Sentry, Notion and more in one click. Cline gets tools to use these apps to retrieve context and act on your behalf.

Cline Desktop is now available on Linux. (This is an early beta so feedback is welcome! 🙏) Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Space Bunny Alpha, or BYOK with any provider!

Sonnet 5.5 beats Opus 5.5 on Terminal-Bench 4.0 at half the cost. It uses far fewer tokens than previous models to do the same work, showing costs reduced up to 30% per task. It also generates output 30% faster than its predecessor, making it the fastest Sonnet model to date.

Trending on OpenRouter and climbing the ranks to #2 top coding agent after our desktop app release!

Ember-1 by the Fireworks Research team is built on Kimi K3, and uses ~40% fewer tokens while achieving the same performance on benchmarks. This was accomplished by post-training K3 to think less repetitively. Reasoning models spend most of their output tokens (sometimes 90%+) on thinking before they answer, which gets expensive in agentic loops where the model tends to re-think the same thoughts on every step. Fireworks RL trained on real agentic coding task loops to teach the model which reasoning actually changes the answer vs which is just looping. In a live A/B test on coding traffic, Ember-1 used 71% fewer reasoning tokens and 39% fewer total tokens than K3 at the same success rate.

Pixel Canary (stealth model) has just released and is free in Cline. It's tied with GPT-6 Astra and beats Kimi K3 on Next.js Agent Evals, a benchmark for real Next.js tasks for web and mobile development.

New in Cline Desktop: SSH support! The app stays on your laptop while Cline works on e.g. a dev server, raspberry pi, docker container, anything you can SSH into. Docs (w/ some videos & getting started guide on SSH): docs.cline.bot/usage/cline-d…

New in Cline Desktop v0.0.34: > Worktrees - run multiple tasks in parallel each on its own branch in ~/.cline/worktrees/<id> > GitHub PR status - see branch’s PR link, merge status, and CI checks (needs gh) > Parallel subagents - delegate multiple tasks at once in each session