MiMo-V2.5 vs Muse Spark 1.3 (Max)
Which is better for the money: MiMo-V2.5 by Xiaomi or Muse Spark 1.3 (Max) by Meta? 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
Muse Spark 1.3 (Max) scores 26.3 points higher (48.1 vs 21.8) but costs 32× as much to run the benchmark ($2000 vs $61.9; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Muse Spark 1.3 (Max) when you need intelligence above 21.8, and MiMo-V2.5 when 21.8 is enough.
| Metric | MiMo-V2.5 | Muse Spark 1.3 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 21.8 | 48.1 | +120.6% Muse Spark 1.3 (Max) is 2.2× more intelligent |
| Total AA cost (lower is better) | $61.93 | $2,000.35 | +3130.0% Muse Spark 1.3 (Max) is 32× more expensive |
| End-to-end time (lower is better) | 46.61s | 75.86s | +62.8% Muse Spark 1.3 (Max) is 62.8% slower |
| Price per 1M tokens (in / out) | $0.13 / $0.27 | $1.25 / $4.25 | |
| Input modalities | Text, Image | Text, Image, Video |
Muse Spark 1.3 (Max) vs MiMo-V2.5: 120.6% more intelligence, 3130.0% more cost to run the AA benchmark, and 62.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
- Muse Spark 1.3 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
MiMo-V2.5Muse Spark 1.3 (Max)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/mimo-v2-5-0424/muse-spark-1-3 · Markdown: /api/v1/compare/mimo-v2-5-0424/muse-spark-1-3?format=md · llms.txt · agent skill