Qwen3.5 4B (Non-reasoning)
AlibabaQwenOpen WeightApache 2.0 · Uso Comercial
Descripción
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.
Fecha de lanzamiento
2026-03-02
Parámetros
4.0B
Longitud del contexto
—
Modalidades
—
Radar de capacidades
10
general
20
coding
71
reasoning
52
science
70
agents
50
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 107 | 28.0 | LS |
| Ranking de codificación | 452 | 27.0 | AA |
| Ranking general | 362 | 37.0 | AA |
| Ciencia | 363 | 41.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
79.9%Aut.
VITA-Bench
22.0%Aut.
DeepPlanning
17.6%Aut.
Chat
IFEvalGoogle Research (2023)
89.8%Aut.
Multi-Challenge
49.0%Aut.
General
C-Eval
85.1%Aut.
MAXIFE
78.0%Aut.
Include
71.0%Aut.
NOVA-63
54.3%Aut.
Instruction Following
IFBench
59.2%Aut.
Language
MMLU-Redux
88.8%Aut.
MMLU-Pro
79.1%Aut.
MMMLU
76.1%Aut.
MMLU-ProX
71.5%Aut.
WMT24++
66.6%Aut.
Long Context
LongBench v2
50.0%Aut.
Math
HMMT25
76.8%Aut.
HMMT 2025
74.0%Aut.
PolyMATH
51.1%Aut.
Reasoning
Global PIQA
78.9%Aut.
GPQANYU + Cohere + Anthropic (2023)
76.2%Aut.
AA-LCR
57.0%Aut.
LiveCodeBench v6
55.8%Aut.
SuperGPQA
52.9%Aut.
Tool Calling
BFCL-V4
50.3%Aut.
Índices de evaluación AA
(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 121.3
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 Banking4.3
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Language80
Biology80
Chat70
Instruction Following70
Legal70
Math70
Physics70
Structured Output70
Finance70
Healthcare70
Tool Calling70
Reasoning60
General60
Chemistry60
Long Context50
Multimodal50
Spatial Reasoning50
Communication50
Economics50
Vision50
Agents40
Precios
Precio de entrada$0.03 / 1M tokens
Precio de salida$0.15 / 1M tokens
Precio mixto (3:1)$0.06 / 1M tokens
Velocidad
Tokens/seg22.2
Retraso del primer token0.71s
Tiempo hasta la respuesta0.71s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
1 proveedores
ProveedorEntradaSalida
1AlibabaPRINCIPAL
$0.03
$0.15
Comparar precios entre diferentes proveedores de API para este modelo.