Claude Fable 5.1 vs Claude Sonnet 5.5

Where it leads

• Higher Arena Text score, 1501 Elo vs 1476 Elo
• Higher FrontierMath Tiers 1-3 (v2) score, 90.2% vs 88.8%
• Higher SimpleQA Verified score, 70.8% vs 46.5%

Best for

• Long-horizon agentic coding where a large prompt prefix is replayed across many turns
• Work where Claude Opus 5 at higher effort has already been evaluated and fell short

Watch out for

• Base input and output pricing is unchanged from Fable 5 at $10 / $50; the saving is entirely in cache reads, so a workload with little cache reuse sees no discount
• 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 are not directly comparable across generations
• Anthropic’s launch comparisons are self-reported and were not reproduced independently here

Where it leads

• Lower input and output prices, $2 and $10 vs $10 and $50 per 1M tokens
• Cheaper cached input, $0.10 vs $0.25 per 1M tokens
• Cheaper batch processing, $20 vs $100 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