Inference
EN

Claude Fable 5 vs Muse Spark 1.3

Change models
Claude Fable 5Anthropic
Muse Spark 1.3Meta
IndexAll categories, out of 100.
74.0 ±2.7 best
70.1 ±4.0
GapIndex points below the top.
Top
−3.9 · no clear gap
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
56/s
76/s best
EloLMArena rating and rank.
1492 best
1491
ReleasedMonth of release.
2026-06
2026-09
Input / 1MUS dollars per 1M input tokens.
$10.00
$1.25 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$4.25 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
$4.63 best
1K documents20K tokens in, 1K out, each.
$250.00
$29.25 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$335.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
71.4 best
70.4
CodingCode writing and repair.
74.7 best
68.8
ReasoningLogic problems and puzzles.
73.6 best
68.1
MultimodalTasks with images and text.
70.1
—
KnowledgeFacts and expert knowledge.
75.8 best
67.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
64.1
84.4 best
MathMath problems.
76.2 best
68.6

Benchmarks

46 shared
Only Claude Fable 5: 46Only Muse Spark 1.3: 13
Claude Fable 5
Muse Spark 1.3
Artificial Analysis Humanity's Last ExamKnowledge
55.5% best5 / 222
48.7%15 / 222
Artificial Analysis Long Context ReasoningReasoning
82.3%27 / 217
83.0% best18 / 217
Critical Physics TasksReasoning
28.6% best14 / 214
24.9%21 / 214
OTIS Mock AIME 2024-2025Math
99.7% best14 / 200
99.2%19 / 200
Artificial Analysis GPQA DiamondKnowledge
92.6%17 / 199
93.5% best8 / 199
Artificial Analysis Omniscience AccuracyKnowledge
65.4% best4 / 164
43.6%41 / 164
GDPval-AA normalizedAgentic
55.5%18 / 133
59.0% best10 / 133
Vibe Code Bench v1.1Coding
90.4% best4 / 123
82.9%23 / 123
Artificial Analysis SciCodeCoding
61.0% best6 / 114
58.8%14 / 114
Chess PuzzlesReasoning
47.0% best24 / 90
37.0%39 / 90
FrontierMath-Tiers-1-3-v2-PrivateMath
87.0% best12 / 90
74.0%25 / 90
Legal Research BenchLegal
49.5% best9 / 90
40.9%33 / 90
Terminal-Bench 2.1 · BenchLMAgentic
84.3%22 / 86
88.8% best7 / 86
Tax Agent BenchFinance
38.3% best12 / 82
37.9%14 / 82
LiveBench Data AnalysisReasoning
80.5% best8 / 80
79.6%13 / 80
LiveBench ReasoningReasoning
89.7%15 / 80
89.7%15 / 80
Mystery Game PuzzlesReasoning
52.0% best14 / 80
25.0%37 / 80
Finance Agent (v2)Finance
56.3%19 / 79
58.9% best8 / 79
Code MigrationCoding
55.1% best10 / 77
27.6%44 / 77
EMBFinance
73.7% best5 / 75
62.7%31 / 75