Claude Opus 5.5 vs Claude Sonnet 5.5

Where it leads

• Higher Arena Text score, 1509 Elo vs 1477 Elo
• Higher Arena WebDev score, 1810 Elo vs 1770 Elo
• Higher FrontierMath Tiers 1-3 (v2) score, 91.2% vs 88.8%
• Higher SimpleQA Verified score, 72.2% vs 46.5%

Best for

• Long-running agentic coding and knowledge work as the general-purpose default
• Cache-heavy agent loops where the 0.05x read multiplier compounds

Watch out for

• The API effort default is medium here, not high as on Claude Fable 5.1 and Claude Sonnet 5.5, so a like-for-like comparison has to set effort explicitly
• The 4.7-generation tokenizer produces roughly 30% more tokens for the same text than Claude Sonnet 4.6 and earlier, so per-token rates do not compare directly across generations

Where it leads

• Lower input and output prices, $2 and $10 vs $4 and $20 per 1M tokens
• Higher GPQA Diamond score, 95.6% vs 90.6%
• Cheaper cached input, $0.10 vs $0.20 per 1M tokens
• Cheaper batch processing, $20 vs $40 for 10M input and 2M output tokens

Best for

• Production workloads that need frontier-adjacent quality at a mid-tier rate
• Latency-sensitive agent steps inside a larger pipeline

Watch out for

• Same list price as Claude Sonnet 5, so the gain is capability and cache economics rather than a cheaper rate card
• Anthropic positions Opus 5.5 rather than this as the default, so reach for Sonnet 5.5 when latency matters more than peak capability