Claude Opus 5 (Medium) vs GPT-6 Luna (Max)
Which is better for the money: Claude Opus 5 (Medium) by Anthropic or GPT-6 Luna (Max) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Claude Opus 5 (Medium) scores 6.7 points higher (44.8 vs 38.1) but costs 22× as much to run the benchmark ($2732 vs $122; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Opus 5 (Medium) when you need intelligence above 38.1, and GPT-6 Luna (Max) when 38.1 is enough.
| Metric | Claude Opus 5 (Medium) | GPT-6 Luna (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 44.8 | 38.1 | −15.0% GPT-6 Luna (Max) is 15.0% less intelligent |
| Total AA cost (lower is better) | $2,731.91 | $122.05 | −95.5% GPT-6 Luna (Max) is 95.5% cheaper |
| End-to-end time (lower is better) | 12.85s | 86.79s | +575.4% GPT-6 Luna (Max) is 575.4% slower |
| Price per 1M tokens (in / out) | $5.00 / $25.0 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Max) vs Claude Opus 5 (Medium): 15.0% less intelligence, 95.5% less cost to run the AA benchmark, and 575.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Opus 5 (Medium) is off the frontier: at the same or lower cost, Claude Opus 5.5 (High, Default Fallback) scores 53.60 for $2172.
- GPT-6 Luna (Max) is on today's frontier: nothing is both smarter and cheaper.
Claude Opus 5 (Medium)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-opus-5-medium/gpt-6-luna · Markdown: /api/v1/compare/claude-opus-5-medium/gpt-6-luna?format=md · llms.txt · agent skill