Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention and extended reasoning. Supports text, image, and video input with a 256K context window.
Added Feb 16, 2026
Model weightsContext Window
258.0K
Max Output
65.5K
Avg output tokens (7d)
2.4K tokens
Input Price (Auto)
$0.39/1M
Output Price (Auto)
$2.34/1M
Cache Read (Auto)
$0.20/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
34.3
Coding Index
48.2
Agentic Index
19.8
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
89.3%
Better than 90% of models compared
HLE
Humanity's Last Exam
29.0%
Better than 84% of models compared
IFBench
Instruction-following benchmark
78.8%
Better than 97% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
95.6%
Better than 95% of models compared
AA-LCR
Long context reasoning evaluation
72.7%
Better than 85% of models compared
GDPval-AA
Economically valuable tasks
23.3%
CritPt
Research-level physics reasoning
1.7%
Coding
SciCode
Python programming for scientific computing
42.0%
Better than 77% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
40.9%
Better than 87% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
30.8%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
88.9%
Last updated Aug 18, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Qwen3.5 397B A17B Thinking with similar models from the same provider or model family.
Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17bQwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Supports text, image, and video input with a 256K context window.
Qwen 3.8 27B Fable
qwen/qwen3.8-27b-fableQwen 3.8 27B Fable is an open-weight multimodal creative finetune for expressive dialogue, long-form storytelling, character work, and roleplay.
Qwen3.8 2.4T A95B (Max)
qwen/qwen3.8-2.4t-a95bThis is the same underlying model as Qwen3.8 Max, exposed under its architecture-based 2.4T A95B name for easier discovery. It uses the identical routing, pricing, capabilities, and non-thinking mode.
Qwen 3.8 27B Uncensored Thinking
qwen/qwen3.8-27b-uncensored:thinkingQwen 3.8 27B Uncensored with thinking enabled for more deliberate creative work, coding, multimodal analysis, tool use, and long-context problem solving.
Qwen 3.6 35B A3B Uncensored Thinking
qwen/qwen3.6-35b-a3b-uncensored:thinkingQwen 3.6 35B A3B Uncensored with thinking enabled for more deliberate coding, multimodal analysis, tool use, and complex chat tasks.
Qwen 3.8 27B Obliterated
qwen/qwen3.8-27b-obliteratedQwen 3.8 27B Obliterated is an open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.