Anthropic’s Claude Haiku 5.5 Scores 43 on Artificial Analysis Index

8 Oct 2026, 1:13 am · 4h ago · 1 min read · OfficeChai

Anthropic’s lightweight AI model Claude Haiku 5.5 has achieved a score of 43 on the Artificial Analysis Intelligence Index. The benchmark places the model just behind Moonshot AI’s Kimi K3 while outperforming OpenAI’s GPT-6 Luna. Artificial Analysis evaluates large language models across multiple performance, reasoning, and efficiency metrics. The results highlight rapid advancements in smaller, cost-effective AI architectures designed for high-speed automated workflows. Anthropic continues to optimize its Haiku lineup to provide competitive intelligence scores at lower inference costs and lower latency for global enterprise developers and tech startups building real-time applications.