Cline (@cline)

DeepSeek silently released V4-Pro 0813, up 15.8% on Terminal Bench from their April Preview model, with Fable 5 performance at ~57x cheaper cost. 1.6T param, 49B active, 1M context. This is the best price-to-perfomance model on the market right now. Available in ClinePass now!

We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container. So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added them to the Cline harness. TL;DR of this special prompting: - Trust source code over the user prompt, so read every call site and existing tests before starting the task - Weigh edge and error cases as heavily as the happy path - Always reproduce the bug before fixing - Don't trust the first passing test suite, and verify suspicious looking half-baked tests - Never stop at just editing, keep working until the change is verified complete. We then asked this modified harness to fix a real bug from our repo, and compared the results to the original Cline agent harness. Results: - Used 2.7x fewer tokens (19.7M → 7.2M) - Finished 2x faster (49min → 24min) - Cost 2.4x less ($7.69 → $3.25) Same Muse Spark 1.2 model, same task, only the prompting changed. Incredible how much of a performance gain Meta was able to achieve training it on these special instructions!

While DeepSeek V4-Flash is significantly cheaper on price per token, this can be misleading if the overall cost per task ends up being higher due to more turns being made. However, @ArtificialAnlys reports DeepSeek completing the same benchmark tasks as Fable at 105x lower cost.

We tested Kimi K3 and Fable on a real bug from the Cline repo, and found that while both models were able to fix it - Fable wins on speed & Kimi wins on cost. - Kimi used 1.7x more tokens than Fable (1.2M vs. 730K) - Fable finished 3.4x faster - 3.5 min and 18 tool calls vs. Kimi’s 12 min and 34 tool calls. - Kimi cost 2.3x less ($0.92 vs. $2.13) thanks to its 3.3x per-token discount Both runs used the same Cline harness, and the traces indicate that Kimi is RL trained to spend more tokens thinking and verifying before completing. This is the first time we've seen an open weight model compete head to head with SOTA. Congratulations to the @Kimi_Moonshot team on this milestone!

We’ve been impressed with GLM-5.2 and so are introducing a $9.99/month subscription to give you 2-5x discounted access to it and other open weight models like DeepSeek, Kimi, MiniMax, Mimo, Qwen. Use it on Cline CLI & IDE with $1.99 special promo if sign up via: npm i -g cline

We've kept hearing how GLM-5.2 beats Opus 4.8, and are skeptical of benchmarks - so we tested them on a real bug from the Cline repo. While both models fixed the issue, GLM was the winner in terms of cost and code quality: - GLM used twice as many tokens (GLM 1.1m vs Opus 660K) but cost half as much (GLM $0.41 vs Opus $0.81) - Opus finished quicker - 1.6 min and 12 tool calls vs GLM 4.7 min and 28 tool calls - GLM cleaned up dead code and verified the build compiled before completing. Opus didn't - it left type errors that passed tests but broke the production build. Both runs used the same Cline harness prompting and tools, so it seems GLM is RL trained to spend more tokens verifying its work before completing. Impressive work by the @Zai_org team!

Introducing the Cline SDK. We rebuilt the Cline harness for our extension and CLI from scratch using all the lessons learned since creating one of the world's first coding agents in 2024, and are open sourcing it for others to build with today. npm i @​cline/sdk 🧵