Claude Haiku 5.5 (High) vs GPT-6 Luna (Max)
Which is better for the money: Claude Haiku 5.5 (High) by Anthropic or GPT-6 Luna (Max) 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
GPT-6 Luna (Max) scores 0.3 points higher (38.1 vs 37.8) but costs 1.3× as much to run the benchmark ($122 vs $94.1; both mid-range class). Pick GPT-6 Luna (Max) when the extra intelligence is worth the premium, otherwise Claude Haiku 5.5 (High).
| Metric | Claude Haiku 5.5 (High) | GPT-6 Luna (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 37.8 | 38.1 | +0.8% GPT-6 Luna (Max) is 0.8% more intelligent |
| Total AA cost (lower is better) | $94.07 | $122.05 | +29.7% GPT-6 Luna (Max) is 29.7% more expensive |
| End-to-end time (lower is better) | 26.02s | 82.02s | +215.2% GPT-6 Luna (Max) is 215.2% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Max) vs Claude Haiku 5.5 (High): 0.8% more intelligence, 29.7% more cost to run the AA benchmark, and 215.2% slower 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.
- GPT-6 Luna (Max) is on today's frontier: nothing is both smarter and cheaper.
Claude Haiku 5.5 (High)GPT-6 Luna (Max)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/gpt-6-luna · Markdown: /api/v1/compare/claude-haiku-5-5-high/gpt-6-luna?format=md · llms.txt · agent skill