Browser Use(@browser_use)

Haiku 5.5 on Browser Use Bench v2.1 👀 > same performace as Luna > 2.8x more expensive Haiku...

7.2内容质量
Haiku 5.5 on Browser Use Bench v2.1 👀 > same performace as Luna > 2.8x more expensive Haiku...

TL;DR · AI 摘要

Haiku 5.5在Browser Use Bench v2.1上性能与Luna相当，但价格是其2.8倍，长上下文任务成本激增5倍。

核心要点

  • Haiku 5.5与Luna性能相同但价格高2.8倍
  • 100k上下文后Haiku成本变为5倍
  • BU Bench 2.1侧重长时序任务

结构提纲

按章节快速跳转。

  1. §性能对比

    Haiku 5.5与Luna在BU Bench v2.1上表现相同。

  2. ·成本分析

    Haiku价格是Luna的2.8倍，长上下文任务成本激增5倍。

  3. ›基准特性

    BU Bench 2.1包含大量长时序任务，导致高频触及高价层级。

思维导图

用一张图看清主题之间的关系。

查看大纲文本（无障碍 / 无 JS 友好）
  • Haiku 5.5性能与成本分析
    • 性能对比
      • 与Luna同级
    • 成本结构
      • 2.8倍基准价
      • 5倍长上下文价
    • 基准特性
      • 长时序任务主导

金句 / Highlights

值得收藏与分享的关键句。

#Haiku#Luna#成本分析#基准测试
打开原文

Browser Use on X: "Haiku 5.5 on Browser Use Bench v2.1 👀 > same performace as Luna > 2.8x more expensive Haiku gets 5x more expensive after 100k context, including cached tokens. BU Bench 2.1 is mostly extremely long-running horizon tasks. It hits that pricing tier a lot." / X

Browser Use

@browser_use

Haiku 5.5 on Browser Use Bench v2.1 👀 > same performace as Luna > 2.8x more expensive Haiku gets 5x more expensive after 100k context, including cached tokens. BU Bench 2.1 is mostly extremely long-running horizon tasks. It hits that pricing tier a lot.

12:22 AM · Oct 8, 2026

·

6,065

Views

9

6

78

17