Claude Opus 5 (High) vs GPT-6 Luna (Non-reasoning)
Which is better for the money: Claude Opus 5 (High) by Anthropic or GPT-6 Luna (Non-reasoning) 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 Opus 5 (High) scores 29.6 points higher (48.1 vs 18.5) but costs 226× as much to run the benchmark ($4332 vs $19.2; flagship vs budget cost classes). They are not alternatives at one budget: pick Claude Opus 5 (High) when you need intelligence above 18.5, and GPT-6 Luna (Non-reasoning) when 18.5 is enough.
| Metric | Claude Opus 5 (High) | GPT-6 Luna (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 48.1 | 18.5 | −61.5% GPT-6 Luna (Non-reaso… is 61.5% less intelligent |
| Total AA cost (lower is better) | $4,331.68 | $19.16 | −99.6% GPT-6 Luna (Non-reaso… is 99.6% cheaper |
| End-to-end time (lower is better) | 29.14s | 5.06s | −82.6% GPT-6 Luna (Non-reaso… is 82.6% faster |
| Price per 1M tokens (in / out) | $5.00 / $25.0 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Non-reasoning) vs Claude Opus 5 (High): 61.5% less intelligence, 99.6% less cost to run the AA benchmark, and 82.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Opus 5 (High) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
- GPT-6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Claude Opus 5 (High)GPT-6 Luna (Non-reasoning)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-high/gpt-6-luna-non-reasoning · Markdown: /api/v1/compare/claude-opus-5-high/gpt-6-luna-non-reasoning?format=md · llms.txt · agent skill