Claude Haiku 5.5 tops GPT-6 Luna on benchmarks, with 2x faster token output
Original title (Chinese)
Claude Haiku 5.5 benchmark 全面领先 GPT-6 Luna,OpenRouter 观测的 token 输出速度也是 2 倍
AISummary
Anthropic's Claude Haiku 5.5, released alongside Claude Opus 5.5 and Claude Sonnet 5.5, is reported to lead GPT-6 Luna across benchmarks, with OpenRouter measuring roughly twice the token output speed.
Anthropic says Haiku 5.5 is its cheapest, fastest, and most capable small model, costing about 75% less to run than Claude Haiku 4.5 on average. The post also notes some CodeX users are reportedly migrating to Claude Code.
Source: meng shao · x.comPublished · added here