Inference
EN

Muse Spark Open vs Muse Wonder

Change models
Muse Spark OpenMeta
Muse WonderMeta
IndexAll categories, out of 100.
65.1 ±3.9
73.1 ±4.0 best
GapIndex points below the top.
−8.0
Top
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
86/s best
80/s
EloLMArena rating and rank.
—
1503
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
$1.25 best
$4.00
Output / 1MUS dollars per 1M output tokens.
$4.25 best
$20.00
1K chats2K tokens in, 500 out, each.
$4.63 best
$18.00
1K documents20K tokens in, 1K out, each.
$29.25 best
$100.00
1K agent tasks200K tokens in, 20K out, each.
$335.00 best
$1,200.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
64.8
73.0 best
CodingCode writing and repair.
63.3
72.3 best
ReasoningLogic problems and puzzles.
62.3
73.1 best
MultimodalTasks with images and text.
69.8
—
KnowledgeFacts and expert knowledge.
65.4
68.6 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
74.4
MathMath problems.
64.9
73.5 best

Benchmarks

28 shared
Only Muse Spark Open: 17Only Muse Wonder: 34
Muse Spark Open
Muse Wonder
Artificial Analysis Humanity's Last ExamKnowledge
43.9%30 / 222
50.1% best12 / 222
Artificial Analysis Long Context ReasoningReasoning
78.3%63 / 217
80.7% best37 / 217
Critical Physics TasksReasoning
14.9%51 / 214
28.3% best15 / 214
OTIS Mock AIME 2024-2025Math
98.1%31 / 200
99.4% best17 / 200
Artificial Analysis Omniscience AccuracyKnowledge
42.0% best44 / 164
38.0%59 / 164
GDPval-AA normalizedAgentic
45.1%39 / 133
63.5% best5 / 133
Vibe Code Bench v1.1Coding
76.2%41 / 123
83.1% best22 / 123
Artificial Analysis SciCodeCoding
58.4%17 / 114
60.3% best10 / 114
FrontierMath-Tiers-1-3-v2-PrivateMath
69.8%30 / 90
82.1% best18 / 90
Legal Research BenchLegal
38.5%39 / 90
50.5% best7 / 90
Tax Agent BenchFinance
26.3%42 / 82
36.3% best15 / 82
LiveBench Data AnalysisReasoning
60.2%72 / 80
81.6% best5 / 80
LiveBench ReasoningReasoning
73.7%71 / 80
90.6% best11 / 80
Finance Agent (v2)Finance
61.3% best3 / 79
56.6%18 / 79
Code MigrationCoding
21.2%51 / 77
62.6% best6 / 77
EMBFinance
53.7%51 / 75
67.1% best18 / 75
FrontierMath-Tier-4-v2-PrivateMath
31.7%32 / 72
70.7% best17 / 72
Terminal-Bench 4.0Agentic
6.6%49 / 61
49.5% best11 / 61
DeepSWEAgentic
60.0%41 / 59
78.8% best2 / 59
LiveBench Coding 2.0Coding
73.6%37 / 52
86.2% best20 / 52