MiniMax M1
by MiniMaxRank #159Score 70.8
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
性能概览
评分
70.8
排名
#159
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 | 50.0 | 20% | 10.0 | 2026-08-08T13:28:52.538Z |
Benchmarks benchmark | 71.3 | 30% | 21.4 | 2026-08-08T13:28:52.538Z |
Pricing pricing_tier | 97.8 | 15% | 14.7 | 2026-08-08T13:28:52.538Z |
Context Window context_window | 95.2 | 10% | 9.5 | 2026-08-08T13:28:52.538Z |
Recency recency | 57.0 | 15% | 8.5 | 2026-08-08T13:28:52.538Z |
Output Capacity output_capacity | 76.4 | 10% | 7.6 | 2026-08-08T13:28:52.538Z |
主要驱动因素
positive
Benchmarks
positive
Pricing
$2.20/M output tokens
$2.20
neutral
Capabilities
Supports reasoning, tools, streaming
3/7
positive
Context Window
1M token context window
1M
功能
| 功能 | 支持 |
|---|---|
| 视觉 | 否 |
| 推理 | 是 |
| JSON模式 | 否 |
| 流式输出 | 是 |
| 函数调用 | 是 |
| 网页搜索 | 否 |
价格
输入/百万令牌
$0.55
输出/百万令牌
$2.20
上下文窗口
1000K
最大输出
40K