MODEL PROFILE / EDITION 2026.09
Claude Fable 5.1
Senior teams shipping production frontends who want the strongest all-round model and will pay for it
Balanced model evidence score; rank 1. No rank delta is shown because there is no prior numeric snapshot.
Best for
Senior teams shipping production frontends who want the strongest all-round model and will pay for it
Price & access
$10 in / $50 out per 1M; cache read $0.25 (75% cheaper than Fable 5), cache write $12.50; Anthropic reports ~25% lower typical workload cost and up to ~45% savings on complex agentic coding vs Fable 5
Evidence summary
First-party launch post, Bedrock card, Anthropic pricing page, plus two independent human-preference boards and a third-party SWE-bench Pro leaderboard all place it at or near the top.
Edition status
No prior snapshot. Tracked in the September 2026 baseline.
Strengths
- SWE-bench Pro rank 1 (81.2%) and AA Intelligence Index rank 1 (57)
- Arena WebDev Frontend rank 2 (1796) plus Design Arena Website rank 3 (1330) - strong on both human-preference boards
- Best-documented debugging evidence (Red Hat diagnosed every broken build; Millennium's one-in-a-million crash)
- Cache reads at $0.25 cut agentic loop costs sharply
Tradeoffs
- $10/$50 top-tier pricing
- AA measured TTFT of 266.51 s at max effort
- Anthropic's own table shows Fable 5 ahead on Terminal-Bench 4.0 in the Mythos row - effort settings matter
- Arena row has only 1,893 votes
Score profile
visual 96 · code 97 · agentic 97 · debug 96 · context 92 · speed 46 · value 40
Linked evidence
Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗Evidence source 7 ↗Use the same published data, filters, and side-by-side metrics.