Qwen3 Coder 480B A35B Instruct
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
描述
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.
發布日期
2025-07-22
參數規模
480.0B
上下文長度
262K
支援模態
text
能力雷達圖
38
general
38
coding
52
reasoning
41
science估算
60
agents
0
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Agents
BFCL-v3
68.7%自報
MM-Mind2Web
55.8%自報
Terminal-Bench 2.0
37.5%自報
Code
SWE-Bench Verified
69.6%自報
Aider-Polyglot
61.8%自報
SWE-bench Multilingual
54.7%自報
Multi-SWE-Bench
25.8%自報
Communication
TAU-bench Retail
77.5%自報
TAU-bench Airline
60.0%自報
Language
Spider
31.1%自報
AA 評測指數
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
LLM Stats 分類評分
Structured Output70
Communication70
Finance70
General70
Tool Calling60
Frontend Development60
Multimodal60
Reasoning60
Agents50
Code50
定價
輸入價格$0.3 / 1M tokens
輸出價格$1.8 / 1M tokens
混合價格(3:1)$0.675 / 1M tokens
速度
Tokens/秒66.1 tokens/s
首Token延遲1.63s
首回答延遲1.63s
可用提供商
(LS 內部計價單位)暫無提供商資料