Inference
EN

Claude Fable 5 vs Muse Wonder Full

Change models
Claude Fable 5Anthropic
Muse Wonder FullMeta
IndexAll categories, out of 100.
74.0 ±2.7
77.3 ±5.3 best
GapIndex points below the top.
−3.3 · no clear gap
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
56/s
—
EloLMArena rating and rank.
1492
—
ReleasedMonth of release.
2026-06
2026-10
Input / 1MUS dollars per 1M input tokens.
$10.00
—
Output / 1MUS dollars per 1M output tokens.
$50.00
—
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
—
1K documents20K tokens in, 1K out, each.
$250.00
—
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
—
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.4
78.2 best
CodingCode writing and repair.
74.7
77.3 best
ReasoningLogic problems and puzzles.
73.6
75.6 best
MultimodalTasks with images and text.
70.1
—
KnowledgeFacts and expert knowledge.
75.8 best
71.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
64.1
—
MathMath problems.
76.2
79.6 best

Benchmarks

23 shared
Only Claude Fable 5: 69Only Muse Wonder Full: 19
Claude Fable 5
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
55.5% best5 / 222
53.6%9 / 222
Artificial Analysis Long Context ReasoningReasoning
82.3%27 / 217
83.7% best10 / 217
Critical Physics TasksReasoning
28.6%14 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
65.4% best4 / 164
41.0%46 / 164
LegalBenchLegal
88.6% best1 / 149
87.4%4 / 149
GDPval-AA normalizedAgentic
55.5%18 / 133
67.9% best2 / 133
Vibe Code Bench v1.1Coding
90.4% best4 / 123
86.0%14 / 123
Artificial Analysis SciCodeCoding
61.0%6 / 114
62.6% best4 / 114
MedScribeHealthcare
88.5%12 / 109
89.3% best8 / 109
MedCodeHealthcare
56.1% best4 / 106
49.9%18 / 106
Legal Research BenchLegal
49.5%9 / 90
53.4% best6 / 90
Tax Agent BenchFinance
38.3%12 / 82
43.0% best8 / 82
Finance Agent (v2)Finance
56.3%19 / 79
59.1% best6 / 79
Code MigrationCoding
55.1%10 / 77
61.0% best7 / 77
EMBFinance
73.7% best5 / 75
71.9%10 / 75
ProgramBenchCoding
2.0% best11 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
41.4%14 / 61
58.1% best6 / 61
Agent Arena steerabilityAgentic
7.915 / 54
9.6 best12 / 54
Agent Arena task outcomeAgentic
5.114 / 54
11.1 best9 / 54
ProofBench v1.1Math
95.0% best10 / 54
94.0%11 / 54