Skip to main content

Qwen3.5 0.8B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen3.5-0.8B is a 0.8 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 features both thinking and non-thinking modes.

Release Date
2026-03-02
Parameters
800M
Context Length
131K
Modalities
text

Capability Radar

30
general
0
coding
40
reasoning
9
scienceest.
20
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

Domain#RankScoreSource
Agentic Capability144
27.0
LS

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench11.6%SR

Chat

IFEvalGoogle Research (2023)44.0%SR
Multi-Challenge18.9%SR

General

C-Eval50.5%SR
NOVA-6342.4%SR
Include40.6%SR
MAXIFE39.2%SR

Instruction Following

IFBench21.0%SR

Language

MMLU-Redux59.5%SR
MMMLU44.3%SR
MMLU-Pro42.3%SR
MMLU-ProX34.6%SR
WMT24++27.2%SR

Long Context

LongBench v226.1%SR

Math

PolyMATH8.2%SR

Reasoning

Global PIQA59.4%SR
SuperGPQA21.3%SR
GPQANYU + Cohere + Anthropic (2023)11.9%SR
AA-LCR4.7%SR

Tool Calling

BFCL-V425.3%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
40
Math
40
Structured Output
40
Chat
30
Instruction Following
30
Legal
30
Physics
30
Reasoning
30
Finance
30
General
30
Healthcare
30
Long Context
20
Agents
20
Chemistry
20
Communication
20
Economics
20
Tool Calling
20
Multimodal
10
Spatial Reasoning
10
Biology
10
Vision
10

Pricing

Input Price$0.18 / 1M tokens
Output Price$0.7 / 1M tokens
Blended Price (3:1)$0.31 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1AlibabaPRIMARY
$0.18
$0.7

Compare pricing across different API providers for this model.

External Sources