01 Primary source
Moonshot AI
Kimi K3
A native multimodal 2.8T-class model for long-horizon coding, knowledge work, and million-token contexts.
TOTAL2.8T
ACTIVE104B
EXPERTS896
Long-horizon agentsView intelligence
MODEL INTELLIGENCE
The sparse model index.
Architecture, context, license, runtime, and deployment evidence for the models shaping expert-routed AI.
No universal rankings. No unsourced numbers. No model-card copy paste.
05 RECORDSUPDATED AUG 2026 · PRIMARY SOURCES
02 Primary source
DeepSeek
DeepSeek V4 Pro
A frontier-scale model combining fine-grained sparse experts with a million-token context for agentic work.
TOTAL1.6T
ACTIVE49B
EXPERTS384
Frontier open reasoningView intelligence
03 Primary source
Z.ai
GLM-5.2
An open flagship designed for long engineering trajectories across a sourced million-token context.
TOTAL753B
ACTIVEUnknown
EXPERTS256
Long-horizon codingView intelligence
04 Primary source
Gemma 4 26B A4B IT
A compact multimodal MoE with 25.2B total and 3.8B active parameters, designed for accessible inference.
TOTAL25.2B
ACTIVE3.8B
EXPERTS128
Single-accelerator baselineView intelligence
05 Primary source
Qwen Team
Qwen3-30B-A3B
A 30.5B-parameter reference MoE with 3.3B active parameters and a broadly accessible artifact footprint.
TOTAL30.5B
ACTIVE3.3B
EXPERTS128
Accessible MoE developmentView intelligence