Private AI
Qwen3.6 35B A3B Uncensored Aggressive is a native vision-language MoE model tuned to reduce refusal behavior while preserving Qwen3.6 coding, math, and multimodal capabilities. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Added May 23, 2026
Context Window
131.1K
Max Output
131.1K
Avg output tokens (7d)
6.6K tokens
Input Price (Auto)
$0.30/1M
Output Price (Auto)
$1.50/1M
Cache Read (Auto)
$0.15/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
40.0
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
88.8%
Better than 93% of models compared
HLE
Humanity's Last Exam
28.9%
Better than 92% of models compared
IFBench
Instruction-following benchmark
76.6%
Better than 95% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
95.9%
Better than 96% of models compared
AA-LCR
Long context reasoning evaluation
69.7%
Better than 94% of models compared
SciCode
Python programming for scientific computing
46.9%
Better than 91% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
43.9%
Last updated Jul 3, 2026
Artificial AnalysisBetter than 93% of models compared
