Private AI
Qwen3.5 35B A3B is a native vision-language MoE model with hybrid attention designed for efficient inference and strong general performance.
Added Feb 24, 2026
Model weightsContext Window
260.1K
Max Output
65.5K
Input Price (Auto)
$0.24/1M
Output Price (Auto)
$1.89/1M
Cache Read (Auto)
$0.12/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
24.0
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
37.0
Agentic Index
11.8
GPQA Diamond
Graduate-level scientific reasoning
81.9%
Better than 75% of models compared
HLE
Humanity's Last Exam
12.8%
Better than 69% of models compared
IFBench
Instruction-following benchmark
44.5%
Better than 50% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
86.3%
Better than 79% of models compared
AA-LCR
Long context reasoning evaluation
55.3%
Better than 63% of models compared
GDPval-AA
Economically valuable tasks
14.9%
CritPt
Research-level physics reasoning
0.6%
SciCode
Python programming for scientific computing
29.3%
Better than 41% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
10.6%
AA-Omniscience Accuracy
Proportion of correctly answered questions
15.7%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
92.1%
Last updated Aug 1, 2026, 12:00 PM
Artificial AnalysisBetter than 44% of models compared
