Mercury 2.5 LLM 达到每秒 770 个 token。
Mercury 2.5 LLM hits 770 tokens per second

原始链接: https://artificialanalysis.ai/models/mercury-2-5

Mercury 2.5 的智力水平低于平均水平,但在同价位模型中性价比较高。它速度极快且输出相当简洁。该模型支持文本输入和输出,并拥有 26 万 token 的上下文窗口。 Mercury 2.5 在人工智能分析智力指数(Artificial Analysis Intelligence Index)上得分为 12 分,低于同类模型的平均水平(中位数为 13)。在智力指数评估中,它生成了 3500 万 token,相比 8500 万的中位数而言相当简洁。 Mercury 2.5 的定价为每百万输入 token 0.25 美元(价格适中,中位数为 0.25 美元),每百万输出 token 0.75 美元(价格适中,中位数为 0.90 美元)。平均而言,在智力指数上评估 Mercury 2.5 的单次任务成本为 0.06 美元。 Mercury 2.5 的处理速度为每秒 770 token,表现显著迅捷(指数为 109)。

Sorry.
相关文章

原文

Mercury 2.5 is below average in intelligence, but well priced when comparing to other models of similar price. It's also notably fast and fairly concise. The model supports text input, outputs text, and has a 260k tokens context window.

Mercury 2.5 scores 12 on the Artificial Analysis Intelligence Index, placing it below average among comparable models (median: 13). When evaluating the Intelligence Index, it generated 35M tokens, which is fairly concise in comparison to the median of 85M.

Pricing for Mercury 2.5 is $0.25 per 1M input tokens (moderately priced, median: $0.25) and $0.75 per 1M output tokens (moderately priced, median: $0.90). On average, it costs $0.06 per task to evaluate Mercury 2.5 on the Intelligence Index.

At 770 tokens per second, Mercury 2.5 is notably fast (109).

联系我们 contact @ memedata.com