Skip to main content
AITier

Qwen3.5 4B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen3.5-4B is a 4 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 for its size across knowledge, reasoning, coding, and multilingual tasks.

Release Date
2026-03-02
Parameters
4.0B
Context Length
—
Modalities
—

Capability Radar

10
general
20
coding
71
reasoning
52
science
70
agents
50
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability107
28.0
LS
Code Ranking452
27.0
AA
General Ranking362
37.0
AA
Science363
41.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench79.9%SR
VITA-Bench22.0%SR
DeepPlanning17.6%SR

Chat

IFEvalGoogle Research (2023)89.8%SR
Multi-Challenge49.0%SR

General

C-Eval85.1%SR
MAXIFE78.0%SR
Include71.0%SR
NOVA-6354.3%SR

Instruction Following

IFBench59.2%SR

Language

MMLU-Redux88.8%SR
MMLU-Pro79.1%SR
MMMLU76.1%SR
MMLU-ProX71.5%SR
WMT24++66.6%SR

Long Context

LongBench v250.0%SR

Math

HMMT2576.8%SR
HMMT 202574.0%SR
PolyMATH51.1%SR

Reasoning

Global PIQA78.9%SR
GPQANYU + Cohere + Anthropic (2023)76.2%SR
AA-LCR57.0%SR
LiveCodeBench v655.8%SR
SuperGPQA52.9%SR

Tool Calling

BFCL-V450.3%SR

AA Evaluation Indices

(Artificial Analysis)
Tau2(Sierra + U Toronto + Vector Institute (2025))
87.7
Gpqa(NYU + Cohere + Anthropic (2023))
71.2
Lcr(Artificial Analysis)
34.7
Ifbench(Google Research (2023))
33.3
Terminalbench V2 1
21.3
Coding Index(Artificial Analysis)
20.3
Terminalbench Hard(Stanford × Laude Institute (2026))
11.4
Intelligence Index(Artificial Analysis)
10.8
Hle(Center for AI Safety + Scale AI (2025))
8.0
Tau Banking
4.3

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
80
Biology
80
Chat
70
Instruction Following
70
Legal
70
Math
70
Physics
70
Structured Output
70
Finance
70
Healthcare
70
Tool Calling
70
Reasoning
60
General
60
Chemistry
60
Long Context
50
Multimodal
50
Spatial Reasoning
50
Communication
50
Economics
50
Vision
50
Agents
40

Pricing

Input Price$0.03 / 1M tokens
Output Price$0.15 / 1M tokens
Blended Price (3:1)$0.06 / 1M tokens

Speed

Tokens/sec20.6
Time to First Token0.72s
Time to Answer0.72s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1AlibabaPRIMARY
$0.03
$0.15

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis