Claude Haiku 5.5 (Max) vs Claude Sonnet 5.5 (Medium, Default Fallback)
Which is better for the money: Claude Haiku 5.5 (Max) 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.
Clear winner
Verdict
Pick Claude Haiku 5.5 (Max)
Claude Sonnet 5.5 (Medium, Default Fallback) vs Claude Haiku 5.5 (Max): 6.0% less intelligence, 88.4% more cost to run the AA benchmark, and 98.1% faster end-to-end.
| Metric | Claude Haiku 5.5 (Max) | Claude Sonnet 5.5 (Medium, Default Fallback) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 40.8 | −6.0% Claude Sonnet 5.5 (Me… is 6.0% less intelligent |
| Total AA cost (lower is better) | $330.25 | $622.28 | +88.4% Claude Sonnet 5.5 (Me… is 88.4% more expensive |
| End-to-end time (lower is better) | 327.94s | 6.13s | −98.1% Claude Sonnet 5.5 (Me… is 98.1% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- 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.
Claude Haiku 5.5 (Max)Claude Sonnet 5.5 (Medium, Default Fallback)Today's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-haiku-5-5/claude-sonnet-5-5-medium · Markdown: /api/v1/compare/claude-haiku-5-5/claude-sonnet-5-5-medium?format=md · llms.txt · agent skill