Claude Haiku 5.5 (Medium) vs Claude Sonnet 5 (Max)
Which is better for the money: Claude Haiku 5.5 (Medium) by Anthropic or Claude Sonnet 5 (Max) by Anthropic? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Claude Sonnet 5 (Max) scores 3.7 points higher (38.2 vs 34.5) but costs 124× as much to run the benchmark ($6998 vs $56.4; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (Max) when you need intelligence above 34.5, and Claude Haiku 5.5 (Medium) when 34.5 is enough.
| Metric | Claude Haiku 5.5 (Medium) | Claude Sonnet 5 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.5 | 38.2 | +10.7% Claude Sonnet 5 (Max) is 10.7% more intelligent |
| Total AA cost (lower is better) | $56.36 | $6,998.25 | +12317.1% Claude Sonnet 5 (Max) is 124× more expensive |
| End-to-end time (lower is better) | 13.12s | 200.39s | +1427.4% Claude Sonnet 5 (Max) is 1427.4% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Claude Sonnet 5 (Max) vs Claude Haiku 5.5 (Medium): 10.7% more intelligence, 12317.1% more cost to run the AA benchmark, and 1427.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Medium) is on today's frontier: nothing is both smarter and cheaper.
- Claude Sonnet 5 (Max) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
Claude Haiku 5.5 (Medium)Claude Sonnet 5 (Max)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-medium/claude-sonnet-5 · Markdown: /api/v1/compare/claude-haiku-5-5-medium/claude-sonnet-5?format=md · llms.txt · agent skill