Private AI
Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Added Feb 28, 2026
Model weightsContext Window
262.1K
Max Output
65.5K
Input Price (Auto)
$0.55/1M
Output Price (Auto)
$3.50/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
32.0
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
86.1%
Better than 89% of models compared
HLE
Humanity's Last Exam
18.8%
Better than 82% of models compared
IFBench
Instruction-following benchmark
51.6%
Better than 63% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
83.9%
Better than 75% of models compared
AA-LCR
Long context reasoning evaluation
58.0%
Better than 72% of models compared
SciCode
Python programming for scientific computing
41.1%
Better than 82% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
35.6%
Last updated Jun 24, 2026
Artificial AnalysisBetter than 84% of models compared
