Arena 公布 Claude Haiku 5.5 (High) 真实评测结果:Code Arena 1587 分首秀第 30 名
Arena 公布 Anthropic Claude Haiku 5.5 (High) 的真实评测结果,在 Code Arena: WebDev 以 1587 分首秀排名第 30,略在 Pareto 前沿之外。
榜单方给出 Haiku 5.5 在 Code Arena 的实际得分与各档 Claude 模型的成本分差,便于横向权衡性价比。
Real-world results are in for Claude Haiku 5.5 (High) by @AnthropicAI.
Debuting at #30 with 1587 pts in Code Arena: WebDev, this release sits just outside the Pareto frontier while still offering strong cost efficiency. It matches GPT‑6 Luna’s price at $0.10/$0.50 per 1M input/output tokens while scoring six pts higher.
Compared with other Claude models, Haiku 5.5 offers:
- 90% lower cost than Haiku 4.5 at +257 pts
- 95% lower cost than Sonnet 5.5 (High) at -128 pts
- 98% lower cost than Opus 5 (High) at -70 pts
- 99% lower cost than Fable 5.1 (Max) at -157 pts
Congrats to the team at @AnthropicAI on this release!
在 X 查看被引用的帖子Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released.
On average, it costs around 75% less to run than Claude Haiku 4.5.
来源:Arena.ai · x.com
事件后续 · 7+
查看完整事件- 同事件Anthropic 发布 Claude Haiku 5.5,Artificial Analysis 评测得分 43Artificial Analysis 完整文章 · 2026-10-08
- 同事件Anthropic 将 Claude Sonnet 5.5 缓存读取价格减半至每百万 token $0.10Claude · 2026-10-08
- 同事件Anthropic 发布 Claude Haiku 5.5,运行成本平均降低约 75%Anthropic:Newsroom · 2026-10-08
- 同事件Arena 评测:Claude Sonnet 5.5 登顶 Agent Arena 第 3 名但未入 Pareto 前沿Arena · 2026-10-03
- 同事件Arena 开放限时测试 Claude Sonnet 5.5,Direct Mode 可用 48 小时Arena · 2026-09-30
- 同事件Claude Sonnet 5.5 (High) 以 1699 分登 Code Arena: WebDev 第 4 名Arena · 2026-09-30
- 同事件Claude Sonnet 5.5 达到 Artificial Analysis 智能指数第 2 名Artificial Analysis 完整文章 · 2026-09-29