Claude Haiku 5.5 (Medium) vs Claude Opus 5 (Low)
Which is better for the money: Claude Haiku 5.5 (Medium) by Anthropic or Claude Opus 5 (Low) 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 Opus 5 (Low) scores 4.9 points higher (39.4 vs 34.5) but costs 28× as much to run the benchmark ($1561 vs $56.4; premium vs mid-range cost classes). They are not alternatives at one budget: pick Claude Opus 5 (Low) 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 Opus 5 (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.5 | 39.4 | +14.2% Claude Opus 5 (Low) is 14.2% more intelligent |
| Total AA cost (lower is better) | $56.36 | $1,560.91 | +2669.5% Claude Opus 5 (Low) is 28× more expensive |
| End-to-end time (lower is better) | 14.67s | 11.37s | −22.5% Claude Opus 5 (Low) is 22.5% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $5.00 / $25.0 | |
| Input modalities | Text, Image | Text, Image |
Claude Opus 5 (Low) vs Claude Haiku 5.5 (Medium): 14.2% more intelligence, 2669.5% more cost to run the AA benchmark, and 22.5% faster 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 Opus 5 (Low) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Claude Haiku 5.5 (Medium)Claude Opus 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-medium/claude-opus-5-low · Markdown: /api/v1/compare/claude-haiku-5-5-medium/claude-opus-5-low?format=md · llms.txt · agent skill