Claude Haiku 5.5 (High) vs Claude Haiku 5.5 (Low)
Which is better for the money: Claude Haiku 5.5 (High) by Anthropic or Claude Haiku 5.5 (Low) by Anthropic? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Claude Haiku 5.5 (High) scores 8.3 points higher (37.8 vs 29.5) but costs 2.7× as much to run the benchmark ($94.1 vs $34.3; mid-range vs budget cost classes). Pick Claude Haiku 5.5 (High) when the extra intelligence is worth the premium, otherwise Claude Haiku 5.5 (Low).
| Metric | Claude Haiku 5.5 (High) | Claude Haiku 5.5 (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 37.8 | 29.5 | −22.0% Claude Haiku 5.5 (Low) is 22.0% less intelligent |
| Total AA cost (lower is better) | $94.07 | $34.31 | −63.5% Claude Haiku 5.5 (Low) is 63.5% cheaper |
| End-to-end time (lower is better) | 26.02s | 10.19s | −60.8% Claude Haiku 5.5 (Low) is 60.8% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
Claude Haiku 5.5 (Low) vs Claude Haiku 5.5 (High): 22.0% less intelligence, 63.5% less cost to run the AA benchmark, and 60.8% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (High) is on today's frontier: nothing is both smarter and cheaper.
- 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 Haiku 5.5 (High)Claude Haiku 5.5 (Low)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-high/claude-haiku-5-5-low · Markdown: /api/v1/compare/claude-haiku-5-5-high/claude-haiku-5-5-low?format=md · llms.txt · agent skill