Claude Haiku 5.5 (Max) vs GPT-5.6 Luna (Medium)
Which is better for the money: Claude Haiku 5.5 (Max) by Anthropic or GPT-5.6 Luna (Medium) by OpenAI? 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 Haiku 5.5 (Max) scores 18.4 points higher (43.4 vs 25.0) but costs 7.5× as much to run the benchmark ($330 vs $44.3; mid-range vs budget cost classes). They are not alternatives at one budget: pick Claude Haiku 5.5 (Max) when you need intelligence above 25.0, and GPT-5.6 Luna (Medium) when 25.0 is enough.
| Metric | Claude Haiku 5.5 (Max) | GPT-5.6 Luna (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 25.0 | −42.4% GPT-5.6 Luna (Medium) is 42.4% less intelligent |
| Total AA cost (lower is better) | $330.25 | $44.32 | −86.6% GPT-5.6 Luna (Medium) is 86.6% cheaper |
| End-to-end time (lower is better) | 354.68s | 6.64s | −98.1% GPT-5.6 Luna (Medium) is 98.1% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.20 / $1.20 | |
| Input modalities | Text, Image | Text, Image |
GPT-5.6 Luna (Medium) vs Claude Haiku 5.5 (Max): 42.4% less intelligence, 86.6% less cost to run the AA benchmark, and 98.1% faster end-to-end.
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.
- GPT-5.6 Luna (Medium) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
Claude Haiku 5.5 (Max)GPT-5.6 Luna (Medium)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/gpt-5-6-luna-medium · Markdown: /api/v1/compare/claude-haiku-5-5/gpt-5-6-luna-medium?format=md · llms.txt · agent skill