Claude Fable 5.2 (High, Default Fallback) vs Claude Haiku 5.5 (Medium)
Which is better for the money: Claude Fable 5.2 (High, Default Fallback) by Anthropic or Claude Haiku 5.5 (Medium) by Anthropic? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-11-10.
Depends on your budget
Claude Fable 5.2 (High, Default Fallbac… scores 37.2 points higher (61.8 vs 24.6) but costs 98× as much to run the benchmark ($7106 vs $72.7; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Fable 5.2 (High, Default Fallbac… when you need intelligence above 24.6, and Claude Haiku 5.5 (Medium) when 24.6 is enough.
| Metric | Claude Fable 5.2 (High, Default Fallback) | Claude Haiku 5.5 (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 61.8 | 24.6 | −60.2% Claude Haiku 5.5 (Med… is 60.2% less intelligent |
| Total AA cost (lower is better) | $7,105.77 | $72.70 | −99.0% Claude Haiku 5.5 (Med… is 99.0% cheaper |
| End-to-end time (lower is better) | 36.05s | 16.15s | −55.2% Claude Haiku 5.5 (Med… is 55.2% faster |
| Price per 1M tokens (in / out) | $8.00 / $40.0 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
Claude Haiku 5.5 (Medium) vs Claude Fable 5.2 (High, Default Fallback): 60.2% less intelligence, 99.0% less cost to run the AA benchmark, and 55.2% faster end-to-end.
Against the frontier
- Claude Fable 5.2 (High, Default Fallback) is on today's frontier: nothing is both smarter and cheaper.
- Claude Haiku 5.5 (Medium) is on today's frontier: nothing is both smarter and cheaper.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-fable-5-2-high/claude-haiku-5-5-medium · Markdown: /api/v1/compare/claude-fable-5-2-high/claude-haiku-5-5-medium?format=md · llms.txt · agent skill