Tag
coding model
Coding models are tuned for code generation, debugging, refactoring, and terminal workflows, often judged by benchmarks like SWE-bench and Terminal Bench. The category is now splitting into long-context, agent-style tool use, and multimodal variants.
2 articles
Model Releases/Apr 2
GLM-5: Z.AI's new flagship for coding and agents
GLM-5 posts 77.8 on SWE-bench Verified and 56.2 on Terminal Bench 2.0, putting Z.AI in direct competition with top coding models.
Model Releases/Mar 28
Cursor’s Composer 2 started from Kimi
Cursor says Composer 2 began on Moonshot AI’s Kimi base, then added more training. The company says the final model is very different.