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 | 66.7 | 20% | 13.3 | 2026-09-22T15:20:48.815Z |
Benchmarks benchmark | 64.3 | 30% | 19.3 | 2026-09-22T15:20:48.815Z |
Pricing pricing_tier | 97.7 | 15% | 14.7 | 2026-09-22T15:20:48.815Z |
Context Window context_window | 81.2 | 10% | 8.1 | 2026-09-22T15:20:48.815Z |
Recency recency | 55.6 | 15% | 8.3 | 2026-09-22T15:20:48.815Z |
Output Capacity output_capacity | 81.1 | 10% | 8.1 | 2026-09-22T15:20:48.815Z |
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 | 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
$0.23
输出/百万令牌
$2.30
上下文窗口
131K
最大输出
118K