Features
End-to-end model training inside production harness
Curriculum autoresearch platform for task and reward curation
On-policy reinforcement learning for domain specialization
Pareto-dominant specialist models outperforming frontier models
Reduced serving cost vs. generalist frontier models
State-of-the-art medical models: Kos-1 Lite, Kos-1 Experimental
Env-free RL at 1T parameters using Kimi K2.5
Rubric judge training methodology for grading
Training/inference mismatch correction for sim2real gap
Scalable data generation for practical domains without manual labeling
GLM-5.2 open-source flagship model with 1M context
GLM-5V-Turbo multimodal coding model
GLM-5-Turbo agent-optimized base model
AutoGLM autonomous planning and execution agent (50+ steps)
GLM-PC computer-operating agent via screen input
AutoClaw 1-minute PC agent deployment
MaaS high-performance model API services
Model fine-tuning for language and multimodal models
AI search tool with multi-engine integration
General translation with context recognition
GLM PPT/Poster one-click presentation generation
CogAgent-9B open-source GLM-PC base model
End-side deployment with Intel partnership
CodeGeeX smart coding assistant for AIPC
