Inference
EN

Claude Sonnet 5.5 vs Muse Spark 1.3

Change models
Claude Sonnet 5.5Anthropic
Muse Spark 1.3Meta
IndexAll categories, out of 100.
77.2 ±2.6 best
70.1 ±4.0
GapIndex points below the top.
Top
−7.1
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
107/s best
76/s
EloLMArena rating and rank.
1469
1491 best
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00
$1.25 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$4.25 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00
$4.63 best
1K documents20K tokens in, 1K out, each.
$50.00
$29.25 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$335.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
77.5 best
70.4
CodingCode writing and repair.
80.8 best
68.8
ReasoningLogic problems and puzzles.
77.8 best
68.1
MultimodalTasks with images and text.
74.4
—
KnowledgeFacts and expert knowledge.
71.3 best
67.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
41.5
84.4 best
MathMath problems.
76.1 best
68.6

Benchmarks

47 shared
Only Claude Sonnet 5.5: 81Only Muse Spark 1.3: 12
Claude Sonnet 5.5
Muse Spark 1.3
Artificial Analysis Humanity's Last ExamKnowledge
55.0% best6 / 222
48.7%15 / 222
Artificial Analysis Long Context ReasoningReasoning
82.7%23 / 217
83.0% best18 / 217
Critical Physics TasksReasoning
31.4% best7 / 214
24.9%21 / 214
OTIS Mock AIME 2024-2025Math
100.0% best1 / 200
99.2%19 / 200
Artificial Analysis Omniscience AccuracyKnowledge
51.5% best17 / 164
43.6%41 / 164
GDPval-AA normalizedAgentic
66.9% best4 / 133
59.0%10 / 133
Vibe Code Bench v1.1Coding
92.4% best2 / 123
82.9%23 / 123
Artificial Analysis SciCodeCoding
61.0% best6 / 114
58.8%14 / 114
Chess PuzzlesReasoning
59.0% best10 / 90
37.0%39 / 90
FrontierMath-Tiers-1-3-v2-PrivateMath
88.8% best10 / 90
74.0%25 / 90
Legal Research BenchLegal
48.1% best12 / 90
40.9%33 / 90
Tax Agent BenchFinance
42.0% best10 / 82
37.9%14 / 82
LiveBench Data AnalysisReasoning
59.5%73 / 80
79.6% best13 / 80
LiveBench ReasoningReasoning
91.6% best7 / 80
89.7%15 / 80
Mystery Game PuzzlesReasoning
65.0% best7 / 80
25.0%37 / 80
Finance Agent (v2)Finance
58.1%12 / 79
58.9% best8 / 79
Code MigrationCoding
69.8% best1 / 77
27.6%44 / 77
EMBFinance
75.7% best3 / 75
62.7%31 / 75
Terminal-Bench 2.1 · Vals AIAgentic
83.1% best6 / 75
72.3%24 / 75
FrontierMath-Tier-4-v2-PrivateMath
80.5% best11 / 72
46.3%24 / 72