Muse Ember vs Muse Spark Open

Change models
IndexAll categories, out of 100.
64.8 ±8.4
65.1 ±3.9 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
70%
90% best
SpeedOutput tokens per second.
158/s best
86/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-11
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.10 best
$1.25
Output / 1MUS dollars per 1M output tokens.
$0.50 best
$4.25
1K chats2K tokens in, 500 out, each.
$0.45 best
$4.63
1K documents20K tokens in, 1K out, each.
$2.50 best
$29.25
1K agent tasks200K tokens in, 20K out, each.
$30.00 best
$335.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
71.4 best
64.8
CodingCode writing and repair.
72.5 best
63.3
ReasoningLogic problems and puzzles.
63.4 best
62.3
MultimodalTasks with images and text.
—
69.8
KnowledgeFacts and expert knowledge.
37.3
65.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
64.9

Benchmarks

6 shared
Only Muse Ember: 11Only Muse Spark Open: 39
Muse Ember
Muse Spark Open
21.1%126 / 164
42.0% best44 / 164
83.7% best21 / 123
76.2%41 / 123
49.0% best10 / 90
38.5%39 / 90
38.2% best13 / 82
26.3%42 / 82
39.4% best15 / 61
6.6%49 / 61
25.0%2 / 35
25.0%2 / 35