Hacker News-首页· theanonymousone·· 7 天前AI 评分21
DeepSeek V4.1 Flash 1017 (Max)
DeepSeek V4.1 Flash 1017 (Max)
AI 导读
DeepSeek V4.1 Flash 1017 (Max) 模型上线，通过智能能力指数、开放度指数以及智能指数进行性能对比。评测指标涵盖 Token 使用成本、上下文窗口、输出速度与首字延迟等维度。同时针对开源模型纳入了模型规模评估。
正文 · 原文
Intelligence
Capability Indexes
Measures the performance of models on specific capabilities and industries
Openness Index
Intelligence Index Comparisons
Token Use
Cost
Context Window
Speed
Measured by Output Speed (tokens per second)
Latency
Measured by Time (seconds) to First Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
Model Size (Open Weights Models Only)
来源：Hacker News-首页 · artificialanalysis.ai