GPT-5.6 Luna (High) vs GPT-5 mini (High)
Which is better for the money: GPT-5.6 Luna (High) by OpenAI or GPT-5 mini (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Clear winner
Verdict
Pick GPT-5.6 Luna (High)
GPT-5 mini (High) vs GPT-5.6 Luna (High): 47.7% less intelligence, 74.4% more cost to run the AA benchmark, and 446.0% slower end-to-end.
| Metric | GPT-5.6 Luna (High) | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 32.1 | 16.8 | −47.7% GPT-5 mini (High) is 47.7% less intelligent |
| Total AA cost (lower is better) | $108.15 | $188.66 | +74.4% GPT-5 mini (High) is 74.4% more expensive |
| End-to-end time (lower is better) | 12.33s | 67.32s | +446.0% GPT-5 mini (High) is 446.0% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.25 / $2.00 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
GPT-5.6 Luna (High)GPT-5 mini (High)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/gpt-5-6-luna-high/gpt-5-mini · Markdown: /api/v1/compare/gpt-5-6-luna-high/gpt-5-mini?format=md · llms.txt · agent skill