Claude Fable 5.2 (Medium, Default Fallback) vs Claude Haiku 5.5 (Xhigh)
Which is better for the money: Claude Fable 5.2 (Medium, Default Fallback) by Anthropic or Claude Haiku 5.5 (Xhigh) 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 (Medium, Default Fallb… scores 21.8 points higher (56.4 vs 34.6) but costs 17× as much to run the benchmark ($3360 vs $193; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Fable 5.2 (Medium, Default Fallb… when you need intelligence above 34.6, and Claude Haiku 5.5 (Xhigh) when 34.6 is enough.
| Metric | Claude Fable 5.2 (Medium, Default Fallback) | Claude Haiku 5.5 (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 56.4 | 34.6 | −38.7% Claude Haiku 5.5 (Xhi… is 38.7% less intelligent |
| Total AA cost (lower is better) | $3,359.66 | $192.70 | −94.3% Claude Haiku 5.5 (Xhi… is 94.3% cheaper |
| End-to-end time (lower is better) | 27.53s | 82.21s | +198.6% Claude Haiku 5.5 (Xhi… is 198.6% slower |
| Price per 1M tokens (in / out) | $8.00 / $40.0 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
Claude Haiku 5.5 (Xhigh) vs Claude Fable 5.2 (Medium, Default Fallback): 38.7% less intelligence, 94.3% less cost to run the AA benchmark, and 198.6% slower end-to-end.
Against the frontier
- Claude Fable 5.2 (Medium, Default Fallback) is on today's frontier: nothing is both smarter and cheaper.
- Claude Haiku 5.5 (Xhigh) is off the frontier: at the same or lower cost, GPT-6.1 Terra (Medium) scores 38.20 for $190.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-fable-5-2-medium/claude-haiku-5-5-xhigh · Markdown: /api/v1/compare/claude-fable-5-2-medium/claude-haiku-5-5-xhigh?format=md · llms.txt · agent skill