Muse Spark 1.1 vs Muse Spark Open

Change models
IndexAll categories, out of 100.
64.4 ±3.1
64.9 ±3.9 best
GapIndex points below the top.
−0.5 · no clear gap
Top
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
152/s best
86/s
EloLMArena rating and rank.
1479
—
ReleasedMonth of release.
2026-07
2026-10
Input / 1MUS dollars per 1M input tokens.
$1.25
$1.25
Output / 1MUS dollars per 1M output tokens.
$4.25
$4.25
1K chats2K tokens in, 500 out, each.
$4.63
$4.63
1K documents20K tokens in, 1K out, each.
$29.25
$29.25
1K agent tasks200K tokens in, 20K out, each.
$335.00
$335.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
61.7
64.7 best
CodingCode writing and repair.
64.7 best
63.1
ReasoningLogic problems and puzzles.
62.8 best
62.2
MultimodalTasks with images and text.
66.3
69.6 best
KnowledgeFacts and expert knowledge.
67.2 best
65.3
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
67.4
—
MathMath problems.
61.2
64.7 best

Benchmarks

19 shared
Only Muse Spark 1.1: 40Only Muse Spark Open: 26
Muse Spark 1.1
Muse Spark Open
46.2% best24 / 222
43.9%30 / 222
77.7%74 / 217
78.3% best63 / 217
15.1% best50 / 214
14.9%51 / 214
89.8% best38 / 199
89.0%48 / 199
52.1% best14 / 165
42.0%45 / 165
35.6%50 / 133
45.1% best39 / 133
72.2%47 / 124
76.2% best42 / 124
58.8% best14 / 114
58.4%17 / 114
38.0%44 / 91
38.5% best40 / 91
57.8% best20 / 91
56.6%22 / 91
72.5% best48 / 80
60.2%72 / 80
87.7% best27 / 80
73.7%71 / 80
57.2%17 / 79
61.3% best3 / 79
31.1% best39 / 77
21.2%51 / 77
EMBFinance
56.4% best45 / 75
53.7%51 / 75
DeepSWEAgentic
53.3%49 / 59
60.0% best41 / 59
MCP AtlasAgentic
88.1%2 / 52
89.2% best1 / 52
JobBenchAgentic
54.7%13 / 36
61.8% best8 / 36
BabyVisionMultimodal
76.3%3 / 11
80.2% best2 / 11