GPT-6 Luna (Max) vs Muse Spark Open (Xhigh)
Which is better for the money: GPT-6 Luna (Max) by OpenAI or Muse Spark Open (Xhigh) by Meta? 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
Muse Spark Open (Xhigh) scores 0.8 points higher (38.9 vs 38.1) but costs 9.7× as much to run the benchmark ($1185 vs $122; premium vs mid-range cost classes). They are not alternatives at one budget: pick Muse Spark Open (Xhigh) when you need intelligence above 38.1, and GPT-6 Luna (Max) when 38.1 is enough.
| Metric | GPT-6 Luna (Max) | Muse Spark Open (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 38.1 | 38.9 | +2.1% Muse Spark Open (Xhig… is 2.1% more intelligent |
| Total AA cost (lower is better) | $122.05 | $1,184.90 | +870.8% Muse Spark Open (Xhig… is 9.7× more expensive |
| End-to-end time (lower is better) | 82.02s | 17.34s | −78.9% Muse Spark Open (Xhig… is 78.9% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $1.25 / $4.25 | |
| Input modalities | Text, Image | Text, Image, Speech, Video |
Muse Spark Open (Xhigh) vs GPT-6 Luna (Max): 2.1% more intelligence, 870.8% more cost to run the AA benchmark, and 78.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Max) is on today's frontier: nothing is both smarter and cheaper.
- Muse Spark Open (Xhigh) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
GPT-6 Luna (Max)Muse Spark Open (Xhigh)Today's Pareto frontierOpen-weights 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/muse-spark-open · Markdown: /api/v1/compare/gpt-6-luna/muse-spark-open?format=md · llms.txt · agent skill