Qwen3 30B A3B Thinking 2507
by AlibabaRank #199Score 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
#199
24小时变化
+1
7天变化
-9
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 | 66.7 | 20% | 13.3 | 2026-09-22T15:20:48.564Z |
Benchmarks benchmark | 64.7 | 30% | 19.4 | 2026-09-22T15:20:48.564Z |
Pricing pricing_tier | 97.6 | 15% | 14.6 | 2026-09-22T15:20:48.564Z |
Context Window context_window | 78.0 | 10% | 7.8 | 2026-09-22T15:20:48.564Z |
Recency recency | 61.8 | 15% | 9.3 | 2026-09-22T15:20:48.564Z |
Output Capacity output_capacity | 72.2 | 10% | 7.2 | 2026-09-22T15:20:48.564Z |
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
1.1y ago
功能
| 功能 | 支持 |
|---|---|
| 视觉 | 否 |
| 推理 | 是 |
| JSON模式 | 是 |
| 流式输出 | 是 |
| 函数调用 | 是 |
| 网页搜索 | 否 |
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