Skip to content

Qwen3 235B A22B Thinking 2507

by AlibabaRank #195Score 65.3

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
65.3
排名
#195
24小时变化
+1
7天变化
-10
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%13.32026-09-22T15:20:48.815Z
Benchmarks
benchmark
64.330%19.32026-09-22T15:20:48.815Z
Pricing
pricing_tier
97.715%14.72026-09-22T15:20:48.815Z
Context Window
context_window
81.210%8.12026-09-22T15:20:48.815Z
Recency
recency
55.615%8.32026-09-22T15:20:48.815Z
Output Capacity
output_capacity
81.110%8.12026-09-22T15:20:48.815Z

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
neutral
Recency
Released over 1 year ago
1.2y 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
131K
最大输出
118K

相关模型

相关

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