Skip to content

Qwen3 235B A22B Thinking 2507

by AlibabaRank #189Score 65.5

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

性能概览

评分
65.5
排名
#189
24小时变化
0
7天变化
-60
状态
stable
置信度
high

信号评分

信号标准化权重贡献新鲜度
Capabilities
capability
66.720%13.32026-08-08T13:41:12.541Z
Benchmarks
benchmark
64.330%19.32026-08-08T13:41:12.541Z
Pricing
pricing_tier
97.715%14.72026-08-08T13:41:12.541Z
Context Window
context_window
86.010%8.62026-08-08T13:41:12.541Z
Recency
recency
63.815%9.62026-08-08T13:41:12.541Z
Output Capacity
output_capacity
20.010%2.02026-08-08T13:41:12.541Z

主要驱动因素

positive
Benchmarks
positive
Pricing
$2.30/M output tokens
$2.30
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Recency
Released over 1 year ago
1.0y ago

功能

功能支持
视觉
推理
JSON模式
流式输出
函数调用
网页搜索

价格

输入/百万令牌
$0.23
输出/百万令牌
$2.30
上下文窗口
262K
最大输出
262K

相关模型

相关

Qwen3 235B A22B Thinking 2507 Tracker - Performance History | LM Market Cap