Qwen3.5 9B (Non-reasoning)
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
Description
Qwen3.5-9B is a 9 billion parameter vision-language model using Gated DeltaNet hybrid architecture with a 3:1 ratio of linear attention to full softmax attention. It supports 262K native context length and delivers strong performance across knowledge, reasoning, coding, and multilingual tasks.
Release Date
2026-03-02
Parameters
9.0B
Context Length
262K
Modalities
image, text, video
Capability Radar
12
general
24
coding
79
reasoning
57
science
70
agents
60
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 100 | 35.0 | LS |
| Code Ranking | 391 | 35.0 | AA |
| General Ranking | 343 | 40.0 | AA |
| Science | 299 | 47.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
79.1%SR
VITA-Bench
29.8%SR
DeepPlanning
18.0%SR
Chat
IFEvalGoogle Research (2023)
91.5%SR
Multi-Challenge
54.5%SR
General
C-Eval
88.2%SR
MAXIFE
83.4%SR
Include
75.6%SR
NOVA-63
55.9%SR
Instruction Following
IFBench
64.5%SR
Language
MMLU-Redux
91.1%SR
MMLU-Pro
82.5%SR
MMMLU
81.2%SR
MMLU-ProX
76.3%SR
WMT24++
72.6%SR
Long Context
LongBench v2
55.2%SR
Math
HMMT 2025
83.2%SR
HMMT25
82.9%SR
PolyMATH
57.3%SR
Reasoning
Global PIQA
83.2%SR
GPQANYU + Cohere + Anthropic (2023)
81.7%SR
LiveCodeBench v6
65.6%SR
AA-LCR
63.0%SR
SuperGPQA
58.2%SR
Tool Calling
BFCL-V4
66.1%SR
AA Evaluation Indices
(Artificial Analysis)Tau2(Sierra + U Toronto + Vector Institute (2025))85.1
Gpqa(NYU + Cohere + Anthropic (2023))78.6
Lcr(Artificial Analysis)46.0
Ifbench(Google Research (2023))37.8
Coding Index(Artificial Analysis)23.5
Terminalbench V2 121.3
Terminalbench Hard(Stanford × Laude Institute (2026))18.2
Intelligence Index(Artificial Analysis)13.3
Hle(Center for AI Safety + Scale AI (2025))9.4
LLM Stats Category Scores
(LLM Stats (zeroeval))Instruction Following80
Language80
Math80
Biology80
Chat70
Legal70
Physics70
Reasoning70
Structured Output70
Finance70
General70
Healthcare70
Chemistry70
Tool Calling70
Long Context60
Multimodal60
Spatial Reasoning60
Economics60
Vision60
Agents50
Communication50
Pricing
Input Price$0.17 / 1M tokens
Output Price$0.25 / 1M tokens
Blended Price (3:1)$0.19 / 1M tokens
Speed
Tokens/sec81.4
Time to First Token0.43s
Time to Answer0.43s
Provider Price Ranking
Provider Price Ranking
2 providers
Cheapest: DeepInfraMost Expensive: Alibaba
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2AlibabaPRIMARY
$0.17
$0.25
Compare pricing across different API providers for this model.