Saltar al contenido principal
AITier

Qwen3.5 2B (Reasoning)

AlibabaQwenOpen WeightApache 2.0 · Uso Comercial

Descripción

Qwen3.5-2B is a 2 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.

Fecha de lanzamiento
2026-03-02
Parámetros
2.0B
Longitud del contexto
—
Modalidades
—

Radar de capacidades

6
general
3
coding
46
reasoning
22
science
50
agents
30
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica136
32.0
LS
Ranking de codificación489
12.0
AA
Ranking general440
29.0
AA
Ciencia519
17.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench48.8%Aut.
BFCL-V443.6%Aut.

Biology

GPQANYU + Cohere + Anthropic (2023)51.6%Aut.

Chemistry

SuperGPQA37.5%Aut.

Communication

Multi-Challenge33.7%Aut.

Finance

MMLU-Pro66.5%Aut.
MMLU-ProX52.3%Aut.

General

MMLU-Redux79.6%Aut.
IFEvalGoogle Research (2023)78.6%Aut.
C-Eval73.2%Aut.
Global PIQA69.3%Aut.
MMMLU63.1%Aut.
MAXIFE60.6%Aut.
Include55.4%Aut.
NOVA-6346.4%Aut.
IFBench41.3%Aut.
LongBench v238.7%Aut.

Language

WMT24++45.8%Aut.

Long Context

AA-LCR25.6%Aut.

Math

PolyMATH26.1%Aut.

Índices de evaluación AA

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
7.4
Coding Index(Artificial Analysis)
2.9
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.5
Ifbench(Google Research (2023))
0.3
Lcr(Artificial Analysis)
0.3
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0
Terminalbench V2 1
0.0
Scicode(UIUC + Argonne National Lab (2024))
0.0
Hle(Center for AI Safety + Scale AI (2025))
0.0

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Structured Output
60
Instruction Following
60
Language
60
Legal
50
Math
50
Physics
50
Reasoning
50
Finance
50
General
50
Healthcare
50
Agents
50
Biology
50
Tool Calling
50
Chemistry
40
Economics
40
Long Context
30
Multimodal
30
Spatial Reasoning
30
Communication
30
Vision
30

Precios

Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)Gratis

Velocidad

Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s

Ranking de Precios por Proveedor

No hay datos de proveedores disponibles

Fuentes externas

LLM StatsArtificial Analysis