Muse Spark 1.3 vs Muse Wonder

Meta against Meta, the same lab's consecutive models. Prices, scores and speed below are live.

  • Muse Spark 1.3 costs 75% less on blended price ($3.00 against $12.00 per 1M tokens, 3 input to 1 output).
  • Muse Wonder scores higher on the Artificial Analysis Intelligence Index: 43.3 against 36.4.
  • On the 14 benchmarks both have scores on, Muse Spark 1.3 leads on 2 and Muse Wonder on 12.
  • Both read up to 1M tokens of context.
  • Muse Wonder is newer: listed Oct 12, 2026, against Sep 2, 2026.

Side by side

Muse Spark 1.3Muse Wonder
LabMetaMeta
ListedSep 2, 2026Oct 12, 2026
Input per 1M tokens$1.88$6.00
Output per 1M tokens$6.38$30.00
Cached input per 1M$0.23$0.30
Blended (3:1) per 1M$3.00$12.00
Context window1M1M
Max output944K944K
Knowledge cutoff--
Intelligence index36.443.3
Coding index75.8-
ReasoningYesYes
Reads imagesYesYes
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

BenchmarkMuse Spark 1.3Muse Wonder
Design Arena: 3D1394 EloDesign Arena1443 EloDesign Arena
Design Arena: Code1350 EloDesign Arena1386 EloDesign Arena
Design Arena: Data Viz1343 EloDesign Arena1306 EloDesign Arena
Design Arena: Game Dev1342 EloDesign Arena1415 EloDesign Arena
Design Arena: PPTX Slides (agentic)1201 EloDesign Arena1096 EloDesign Arena
Design Arena: UI Component1346 EloDesign Arena1379 EloDesign Arena
Design Arena: Website1355 EloDesign Arena1370 EloDesign Arena
LMArena (Coding)1509 EloLMArena1518 EloLMArena
LMArena (Overall)1491 EloLMArena1499 EloLMArena
LMArena: Creative Writing1464 EloLMArena1488 EloLMArena
LMArena: Hard Prompts1503 EloLMArena1507 EloLMArena
LMArena: Longer Query1488 EloLMArena1495 EloLMArena
LMArena: Math1492 EloLMArena1499 EloLMArena
LMArena: Multi-Turn1488 EloLMArena1505 EloLMArena

In our tests and guides

Where Muse Spark 1.3 or Muse Wonder ran on a real brief, or shows in a live table.

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Meta models, Meta models, every LLM's price and our sources.