Private AI
Qwen3.5 122B A10B is a large MoE model with 122B total parameters, 10B active parameters per token, strong coding and tool-use behavior, and a 262K token context window. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Added May 26, 2026
Context Window
262.1K
Max Output
262.1K
Input Price (Auto)
$0.46/1M
Output Price (Auto)
$3.68/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
9.9
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
1.0
GPQA Diamond
Graduate-level scientific reasoning
23.6%
Better than 3% of models compared
HLE
Humanity's Last Exam
4.9%
Better than 38% of models compared
IFBench
Instruction-following benchmark
21.6%
Better than 4% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
65.2%
Better than 66% of models compared
AA-LCR
Long context reasoning evaluation
6.7%
Better than 21% of models compared
SciCode
Python programming for scientific computing
2.9%
Better than 3% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
0.0%
Last updated May 26, 2026
Artificial AnalysisBetter than 6% of models compared
