Claude Haiku 5.5 (Max) vs GPT-6 Luna (Xhigh)
Which is better for the money: Claude Haiku 5.5 (Max) by Anthropic or GPT-6 Luna (Xhigh) 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 8.8 points higher (43.4 vs 34.6) but costs 4.9× as much to run the benchmark ($330 vs $66.8; both mid-range class). They are not alternatives at one budget: pick Claude Haiku 5.5 (Max) when you need intelligence above 34.6, and GPT-6 Luna (Xhigh) when 34.6 is enough.
| Metric | Claude Haiku 5.5 (Max) | GPT-6 Luna (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 34.6 | −20.3% GPT-6 Luna (Xhigh) is 20.3% less intelligent |
| Total AA cost (lower is better) | $330.25 | $66.81 | −79.8% GPT-6 Luna (Xhigh) is 79.8% cheaper |
| End-to-end time (lower is better) | 318.48s | 21.27s | −93.3% GPT-6 Luna (Xhigh) is 93.3% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Xhigh) vs Claude Haiku 5.5 (Max): 20.3% less intelligence, 79.8% less cost to run the AA benchmark, and 93.3% 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 (Xhigh) is on today's frontier: nothing is both smarter and cheaper.
Claude Haiku 5.5 (Max)GPT-6 Luna (Xhigh)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-xhigh · Markdown: /api/v1/compare/claude-haiku-5-5/gpt-6-luna-xhigh?format=md · llms.txt · agent skill