GPT-6 Luna (Non-reasoning) vs Solar Mini 4
Which is better for the money: GPT-6 Luna (Non-reasoning) by OpenAI or Solar Mini 4 by Upstage? 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
Solar Mini 4 scores 5.6 points higher (24.1 vs 18.5) but costs 26× as much to run the benchmark ($502 vs $19.2; premium vs budget cost classes). They are not alternatives at one budget: pick Solar Mini 4 when you need intelligence above 18.5, and GPT-6 Luna (Non-reasoning) when 18.5 is enough.
| Metric | GPT-6 Luna (Non-reasoning) | Solar Mini 4 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 18.5 | 24.1 | +30.3% Solar Mini 4 is 30.3% more intelligent |
| Total AA cost (lower is better) | $19.16 | $502.02 | +2520.1% Solar Mini 4 is 26× more expensive |
| End-to-end time (lower is better) | 5.07s | 23.11s | +355.8% Solar Mini 4 is 355.8% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.10 / $0.40 | |
| Input modalities | Text, Image | Text |
Solar Mini 4 vs GPT-6 Luna (Non-reasoning): 30.3% more intelligence, 2520.1% more cost to run the AA benchmark, and 355.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- 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.
- Solar Mini 4 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
GPT-6 Luna (Non-reasoning)Solar Mini 4Today'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-6-luna-non-reasoning/solar-mini4 · Markdown: /api/v1/compare/gpt-6-luna-non-reasoning/solar-mini4?format=md · llms.txt · agent skill