跳轉到主要內容

Qwen3.5 9B (Non-reasoning)

AlibabaQwen開源權重Apache 2.0 · 商用許可

描述

Qwen3.5-9B is a 9 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 across knowledge, reasoning, coding, and multilingual tasks.

發布日期
2026-03-02
參數規模
9.0B
上下文長度
262K
支援模態
image, text, video

能力雷達圖

12
general
24
coding
79
reasoning
57
science
70
agents
60
multimodal

排行榜排名

領域#排名分數來源
智慧體能力模型榜100
35.0
LS
程式碼能力榜388
35.0
AA
通用能力榜341
40.0
AA
科學能力296
47.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench79.1%自報
VITA-Bench29.8%自報
DeepPlanning18.0%自報

Chat

IFEvalGoogle Research (2023)91.5%自報
Multi-Challenge54.5%自報

General

C-Eval88.2%自報
MAXIFE83.4%自報
Include75.6%自報
NOVA-6355.9%自報

Instruction Following

IFBench64.5%自報

Language

MMLU-Redux91.1%自報
MMLU-Pro82.5%自報
MMMLU81.2%自報
MMLU-ProX76.3%自報
WMT24++72.6%自報

Long Context

LongBench v255.2%自報

Math

HMMT 202583.2%自報
HMMT2582.9%自報
PolyMATH57.3%自報

Reasoning

Global PIQA83.2%自報
GPQANYU + Cohere + Anthropic (2023)81.7%自報
LiveCodeBench v665.6%自報
AA-LCR63.0%自報
SuperGPQA58.2%自報

Tool Calling

BFCL-V466.1%自報

AA 評測指數

(Artificial Analysis)
Tau2(Sierra + U Toronto + Vector Institute (2025))
85.1
Gpqa(NYU + Cohere + Anthropic (2023))
78.6
Lcr(Artificial Analysis)
46.0
Ifbench(Google Research (2023))
37.8
Coding Index(Artificial Analysis)
23.5
Terminalbench V2 1
21.3
Terminalbench Hard(Stanford × Laude Institute (2026))
18.2
Intelligence Index(Artificial Analysis)
13.3
Hle(Center for AI Safety + Scale AI (2025))
9.4

LLM Stats 分類評分

(LLM Stats (zeroeval))
Instruction Following
80
Language
80
Math
80
Biology
80
Chat
70
Legal
70
Physics
70
Reasoning
70
Structured Output
70
Finance
70
General
70
Healthcare
70
Chemistry
70
Tool Calling
70
Long Context
60
Multimodal
60
Spatial Reasoning
60
Economics
60
Vision
60
Agents
50
Communication
50

定價

輸入價格$0.17 / 1M tokens
輸出價格$0.25 / 1M tokens
混合價格(3:1)$0.19 / 1M tokens

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

2 個供應商

最便宜: DeepInfra最貴: Alibaba
供應商輸入輸出
1DeepInfra最便宜
$0
$0
2Alibaba主要
$0.17
$0.25

比較該模型在不同 API 供應商之間的定價。

外部連結