Claude Opus 4.8 is here. Is it as good as they say?
Lenny's Newsletter1002 字 (约 5 分钟)
87
Opus 4.8 scores 69.2% on Sweet Bench Pro—~5 pts above Opus 4.7, ~10 above GPT-4.5—but real-world coding reveals persistent ‘last 10%’ failures and hallucinations; pricing is steep at $5/k input tokens.
入选理由：Opus 4.8在Sweet Bench Pro上得分69.2%，显著优于Opus 4.7（+5pt）、GPT-4.5（+10pt）和Gemini 3.1（+15pt）
FeaturedArticle#Claude#LLM#Anthropic#AI coding#benchmark英文
