Claude Haiku 5.5 (Low) vs Claude Sonnet 5.5 (Medium, Default Fallback)
Which is better for the money: Claude Haiku 5.5 (Low) by Anthropic or Claude Sonnet 5.5 (Medium, Default Fallback) by Anthropic? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Depends on your budget
Claude Sonnet 5.5 (Medium, Default Fall… scores 11.3 points higher (40.8 vs 29.5) but costs 18× as much to run the benchmark ($622 vs $34.3; premium vs budget cost classes). They are not alternatives at one budget: pick Claude Sonnet 5.5 (Medium, Default Fall… when you need intelligence above 29.5, and Claude Haiku 5.5 (Low) when 29.5 is enough.
| Metric | Claude Haiku 5.5 (Low) | Claude Sonnet 5.5 (Medium, Default Fallback) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.5 | 40.8 | +38.3% Claude Sonnet 5.5 (Me… is 38.3% more intelligent |
| Total AA cost (lower is better) | $34.31 | $622.28 | +1713.7% Claude Sonnet 5.5 (Me… is 18× more expensive |
| End-to-end time (lower is better) | 11.45s | 6.28s | −45.2% Claude Sonnet 5.5 (Me… is 45.2% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Claude Sonnet 5.5 (Medium, Default Fallback) vs Claude Haiku 5.5 (Low): 38.3% more intelligence, 1713.7% more cost to run the AA benchmark, and 45.2% faster end-to-end.
Against the frontier
- Claude Haiku 5.5 (Low) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
- Claude Sonnet 5.5 (Medium, Default Fallback) is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-haiku-5-5-low/claude-sonnet-5-5-medium · Markdown: /api/v1/compare/claude-haiku-5-5-low/claude-sonnet-5-5-medium?format=md · llms.txt · agent skill