Qwen3.5 2B (Reasoning)
AlibabaQwen开源权重Apache 2.0 · 商用许可
描述
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.
发布日期
2026-03-02
参数规模
2.0B
上下文长度
—
支持模态
—
能力雷达图
50
general
0
coding
50
reasoning
43
science估算
50
agents
30
multimodal
缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
| 领域 | #排名 | 分数 | 来源 |
|---|---|---|---|
| 智能体能力模型榜 | 143 | 32.0 | LS |
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
48.8%自报
Chat
IFEvalGoogle Research (2023)
78.6%自报
Multi-Challenge
33.7%自报
General
C-Eval
73.2%自报
MAXIFE
60.6%自报
Include
55.4%自报
NOVA-63
46.4%自报
Instruction Following
IFBench
41.3%自报
Language
MMLU-Redux
79.6%自报
MMLU-Pro
66.5%自报
MMMLU
63.1%自报
MMLU-ProX
52.3%自报
WMT24++
45.8%自报
Long Context
LongBench v2
38.7%自报
Math
PolyMATH
26.1%自报
Reasoning
Global PIQA
69.3%自报
GPQANYU + Cohere + Anthropic (2023)
51.6%自报
SuperGPQA
37.5%自报
AA-LCR
25.6%自报
Tool Calling
BFCL-V4
43.6%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Chat60
Instruction Following60
Language60
Structured Output60
Legal50
Math50
Physics50
Reasoning50
Finance50
General50
Healthcare50
Agents50
Biology50
Tool Calling50
Chemistry40
Economics40
Long Context30
Multimodal30
Spatial Reasoning30
Communication30
Vision30
定价
暂无定价数据
速度
暂无速度数据
供应商价格排行
暂无提供商数据