Qwen3 Coder 480B A35B Instruct
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
Descripción
Qwen3-Coder-480B-A35B-Instruct is Qwen's most agentic code model to date, featuring 480 billion total parameters with 35 billion activated parameters using MoE architecture. It achieves significant performance among open models on Agentic Coding, Agentic Browser-Use, and foundational coding tasks, with results comparable to Claude Sonnet. Features native 256K token context length (extendable to 1M tokens with Yarn), optimized for repository-scale understanding, and specialized function call format for agentic coding platforms like Qwen Code and CLINE.
Fecha de lanzamiento
2025-07-22
Parámetros
480.0B
Longitud del contexto
262K
Modalidades
text
Radar de capacidades
38
general
38
coding
52
reasoning
41
scienceest.
60
agents
0
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Agents & Tools | 55 | 56.0 | LS |
| Code Ranking | 170 | 47.0 | AA |
| General Ranking | 211 | 49.0 | AA |
| Math Reasoning | 170 | 53.0 | AA |
| Science | 249 | 43.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Agents
BFCL-v3
68.7%Aut.
MM-Mind2Web
55.8%Aut.
Terminal-Bench 2.0
37.5%Aut.
Code
SWE-Bench Verified
69.6%Aut.
Aider-Polyglot
61.8%Aut.
SWE-bench Multilingual
54.7%Aut.
Multi-SWE-Bench
25.8%Aut.
Communication
TAU-bench Retail
77.5%Aut.
TAU-bench Airline
60.0%Aut.
Language
Spider
31.1%Aut.
Índices de evaluación AA
Math Index39.3
Intelligence Index24.8
Coding Index24.6
Math 5000.9
Mmlu Pro0.8
Gpqa0.6
Livecodebench0.6
Aime0.5
Tau20.4
Lcr0.4
Ifbench0.4
Aime 250.4
Scicode0.4
Terminalbench Hard0.2
Hle0.0
Puntuaciones por categoría LLM Stats
Structured Output70
Communication70
Finance70
General70
Tool Calling60
Frontend Development60
Multimodal60
Reasoning60
Agents50
Code50
Precios
Precio de entrada$0.3 / 1M tokens
Precio de salida$1.8 / 1M tokens
Precio mixto (3:1)$0.675 / 1M tokens
Velocidad
Tokens/seg66.1 tokens/s
Retraso del primer token1.63s
Tiempo hasta la respuesta1.63s
Proveedores disponibles
(Unidades internas LS)No hay datos de proveedores disponibles