Skip to content

Qwen3 30B A3B Thinking 2507

by AlibabaRank #194Score 64.1

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

性能概览

评分
64.1
排名
#194
24小时变化
0
7天变化
-59
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%13.32026-08-08T13:41:13.091Z
Benchmarks
benchmark
64.730%19.42026-08-08T13:41:13.091Z
Pricing
pricing_tier
97.615%14.62026-08-08T13:41:13.091Z
Context Window
context_window
78.010%7.82026-08-08T13:41:13.091Z
Recency
recency
70.015%10.52026-08-08T13:41:13.091Z
Output Capacity
output_capacity
75.010%7.52026-08-08T13:41:13.091Z

主要驱动因素

positive
Benchmarks
positive
Pricing
$2.40/M output tokens
$2.40
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Recency
Released over 1 year ago
12mo 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
$0.20
输出/百万令牌
$2.40
上下文窗口
82K
最大输出
33K

相关模型

相关

Qwen3 30B A3B Thinking 2507 Tracker - Performance History | LM Market Cap