Saltar al contenido principal

Qwen3.6 Plus

AlibabaQwenProprietary

Descripción

Qwen3.6 Plus is Alibaba's next-generation flagship model featuring a 1 million token native context window, up to 65,536 output tokens, and always-on chain-of-thought reasoning. It uses a next-generation hybrid architecture optimized for efficiency and scalability. It leads on Terminal-Bench 2.0 agentic coding (61.6), surpassing Claude 4.5 Opus, and achieves strong results on document understanding (OmniDocBench 91.2) and multimodal reasoning (MMMU 86.0). Compared to Qwen 3.5, it is significantly more decisive in reasoning, using fewer tokens on straightforward tasks with better agent stability.

Fecha de lanzamiento
2026-04-02
Parámetros
—
Longitud del contexto
1.0M
Modalidades
image, text, video

Radar de capacidades

70
general
60
coding
80
reasoning
77
scienceest.
60
agents
90
multimodal

Science se estima a partir de las puntuaciones científicas de LLM Stats o del razonamiento cuando no hay benchmarks científicos dedicados.

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica47
54.0
LS
Razonamiento matemático48
84.0
LB
Ranking multimodal6
71.0
LS

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

TAU3-Bench70.7%Aut.
MCP-Mark48.2%Aut.
VITA-Bench44.3%Aut.
DeepPlanning41.5%Aut.
Finance Agent v240.8%
Toolathlon39.8%Aut.

Chat

IFEvalGoogle Research (2023)94.3%Aut.

Code

Claw-Eval58.7%Aut.
SkillsBench45.7%Aut.
NL2Repo37.9%Aut.
FrontierSWE22.0%

General

C-Eval93.3%Aut.
MAXIFE88.2%Aut.
Include85.1%Aut.
NOVA-6357.9%Aut.

Instruction Following

IFBench74.2%Aut.

Language

MMLU-Redux94.5%Aut.
MMMLU89.5%Aut.
MMLU-Pro88.5%Aut.
MMLU-ProX84.7%Aut.
WMT24++84.3%Aut.

Long Context

LongBench v262.0%Aut.

Math

HMMT 202596.7%Aut.
AIME 202695.3%Aut.
HMMT2594.6%Aut.
We-Math89.0%Aut.
DynaMath88.0%Aut.
MathVision88.0%Aut.
HMMT Feb 2687.8%Aut.
IMO-AnswerBench83.8%Aut.
PolyMATH77.4%Aut.
LiveBench70.9%

Multimodal

MMMU86.0%Aut.
Video-MME84.2%Aut.
VideoMMMU84.0%Aut.
OSWorld-Verified62.5%Aut.
TIR-Bench61.6%Aut.

Reasoning

GPQANYU + Cohere + Anthropic (2023)90.4%Aut.
Global PIQA89.8%Aut.
LiveCodeBench v687.1%Aut.
CharXiv-R81.5%Aut.
SWE-Bench Verified78.8%Aut.
MCP Atlas74.1%Aut.
SWE-bench Multilingual73.8%Aut.
SuperGPQA71.6%Aut.
AA-LCR68.3%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)61.6%Aut.
SWE-Bench ProPrinceton NLP (2024)56.6%Aut.
Humanity's Last Exam28.8%Aut.

Search

WideSearch74.3%Aut.

Video

MLVU86.7%Aut.

Vision

CountBench0.98 / 100Aut.
V*96.9%Aut.
AI2D94.4%Aut.
RefCOCO-avg0.94 / 100Aut.
OmniDocBench 1.591.2%Aut.
RealWorldQA85.4%Aut.
CC-OCR83.4%Aut.
MMStar83.3%Aut.
MMMU-Pro78.8%Aut.
ScreenSpot Pro68.2%Aut.
SimpleVQA0.67 / 100Aut.
ERQA65.7%Aut.
MMLongBench-Doc0.62 / 100Aut.
ODinW51.8%Aut.

Índices de evaluación AA

(Artificial Analysis)

No hay datos de evaluación AA disponibles

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Chat
90
Language
90
Biology
90
Video
90
Instruction Following
80
Legal
80
Math
80
Multimodal
80
Physics
80
Reasoning
80
Spatial Reasoning
80
Structured Output
80
Frontend Development
80
Grounding
80
Healthcare
80
Chemistry
80
Text-to-image
80
Vision
80
Image To Text
70
Long Context
70
Search
70
Finance
70
General
70
Economics
70
Code
60
Tool Calling
60
Agents
50

Precios

Precio de entrada$0.5 / 1M tokens
Precio de salida$3 / 1M tokens
Precio mixto (3:1)$1.125 / 1M tokens
Precio de lectura caché$0.05 / 1M tokens
Precio de escritura caché$0.625 / 1M tokens

Velocidad

Tokens/seg56.1
Retraso del primer token2.08s
Tiempo hasta la respuesta100.93s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

19 proveedores

Más barato: Alibaba (China)Más caro: Ofox
ProveedorEntradaSalida
1Alibaba (China)Más barato
$0.276
$1.651
2OrcaRouter
$0.276
$1.651
3Merge Gateway
$0.276
$1.651
4AIHubMix
$0.282
$1.692
5302.AI
$0.3
$1.8
6CrossModel
$0.32
$1.88
7NanoGPT
$0.325
$1.95
8OpenRouter
$0.325
$1.95
9Kilo Gateway
$0.325
$1.95
10AlibabaPRINCIPAL
$0.5
$3
11Novita
$0.5
$3
12Together
$0.5
$3
13ZenMux
$0.5
$3
14OpenCode
$0.5
$3
15Requesty
$0.5
$3
16DevPass (LLM Gateway)
$0.5
$3
17LLMTR
$0.5
$3
18EmpirioLabs AI
$0.5
$3
19Ofox
$0.5
$3

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas