# Claude Haiku 5.5 is now available in Arena.ai's Agent Arena and Code Arena

Arena.ai has added Anthropic's Claude Haiku 5.5 to Agent Arena and Code Arena across WebDev, Text, Document, and Vision, with benchmark evaluation scores coming soon.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/93f8abd8a76a4fb0b9093b43.html

Content language: en
Localization state: sameLanguage

Source: Arena.ai · Published 10/7/2026, 12:00:55

Arena.ai has made Anthropic's Claude Haiku 5.5 available in Agent Arena and Code Arena, with benchmark evaluation scores scheduled to follow. In Code Arena, the model is accessible across the WebDev, Text, Document, and Vision tracks.

Agent Arena evaluates models on real-world, long-horizon agentic tasks from users, allowing models to utilize web search, filesystem, and terminal tools to complete workflows. Leaderboard standings measure performance relative to an average model using a causal tracing methodology.

Anthropic introduced Claude Haiku 5.5 as its cheapest and fastest small model to date, stating that it costs approximately 75% less on average to run than Claude Haiku 4.5.

Tags: Arena.ai, Claude Haiku 5.5, Anthropic, AI Benchmarks

[View original post](https://x.com/arena/status/2107906881276826082)