gpt-oss-120b (High) vs Muse Spark Open (Xhigh)
Which is better for the money: gpt-oss-120b (High) by OpenAI or Muse Spark Open (Xhigh) by Meta? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Muse Spark Open (Xhigh) scores 27.3 points higher (38.9 vs 11.6) but costs 9.7× as much to run the benchmark ($1185 vs $123; premium vs mid-range cost classes). They are not alternatives at one budget: pick Muse Spark Open (Xhigh) when you need intelligence above 11.6, and gpt-oss-120b (High) when 11.6 is enough.
| Metric | gpt-oss-120b (High) | Muse Spark Open (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.6 | 38.9 | +235.3% Muse Spark Open (Xhig… is 3.4× more intelligent |
| Total AA cost (lower is better) | $122.71 | $1,184.90 | +865.6% Muse Spark Open (Xhig… is 9.7× more expensive |
| End-to-end time (lower is better) | 11.55s | 17.34s | +50.1% Muse Spark Open (Xhig… is 50.1% slower |
| Price per 1M tokens (in / out) | $0.15 / $0.60 | $1.25 / $4.25 | |
| Input modalities | Text | Text, Image, Speech, Video |
Muse Spark Open (Xhigh) vs gpt-oss-120b (High): 235.3% more intelligence, 865.6% more cost to run the AA benchmark, and 50.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- 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-oss-120b (High)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-oss-120b/muse-spark-open · Markdown: /api/v1/compare/gpt-oss-120b/muse-spark-open?format=md · llms.txt · agent skill