Muse Ember (Xhigh) vs Muse Spark 1.3 (Max)
Which is better for the money: Muse Ember (Xhigh) by Meta or Muse Spark 1.3 (Max) by Meta? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-11-10.
Trade-off
Verdict
Depends on your budget
Muse Spark 1.3 (Max) scores 2.5 points higher (36.6 vs 34.1) but costs 20× as much to run the benchmark ($1906 vs $95.7; premium vs mid-range cost classes). They are not alternatives at one budget: pick Muse Spark 1.3 (Max) when you need intelligence above 34.1, and Muse Ember (Xhigh) when 34.1 is enough.
| Metric | Muse Ember (Xhigh) | Muse Spark 1.3 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.1 | 36.6 | +7.3% Muse Spark 1.3 (Max) is 7.3% more intelligent |
| Total AA cost (lower is better) | $95.73 | $1,905.84 | +1890.8% Muse Spark 1.3 (Max) is 20× more expensive |
| End-to-end time (lower is better) | 9.48s | 44.56s | +370.0% Muse Spark 1.3 (Max) is 370.0% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $1.25 / $4.25 | |
| Input modalities | Text, Image | Text, Image, Video |
Muse Spark 1.3 (Max) vs Muse Ember (Xhigh): 7.3% more intelligence, 1890.8% more cost to run the AA benchmark, and 370.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Muse Ember (Xhigh) is on today's frontier: nothing is both smarter and cheaper.
- Muse Spark 1.3 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 54.60 for $1124.
Muse Ember (Xhigh)Muse Spark 1.3 (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/muse-ember-xhigh/muse-spark-1-3 · Markdown: /api/v1/compare/muse-ember-xhigh/muse-spark-1-3?format=md · llms.txt · agent skill