Claude Haiku 5.5 (Max) vs GPT-6 Luna (Medium)
Which is better for the money: Claude Haiku 5.5 (Max) by Anthropic or GPT-6 Luna (Medium) by OpenAI? 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 (Max) scores 13.5 points higher (43.4 vs 29.9) but costs 11× as much to run the benchmark ($330 vs $31.2; mid-range vs budget cost classes). They are not alternatives at one budget: pick Claude Haiku 5.5 (Max) when you need intelligence above 29.9, and GPT-6 Luna (Medium) when 29.9 is enough.
| Metric | Claude Haiku 5.5 (Max) | GPT-6 Luna (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 29.9 | −31.1% GPT-6 Luna (Medium) is 31.1% less intelligent |
| Total AA cost (lower is better) | $330.25 | $31.17 | −90.6% GPT-6 Luna (Medium) is 90.6% cheaper |
| End-to-end time (lower is better) | 318.48s | 8.25s | −97.4% GPT-6 Luna (Medium) is 97.4% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Medium) vs Claude Haiku 5.5 (Max): 31.1% less intelligence, 90.6% less cost to run the AA benchmark, and 97.4% 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-6 Luna (Medium) is on today's frontier: nothing is both smarter and cheaper.
Claude Haiku 5.5 (Max)GPT-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-6-luna-medium · Markdown: /api/v1/compare/claude-haiku-5-5/gpt-6-luna-medium?format=md · llms.txt · agent skill