Inference
EN

Claude Fable 5.1 vs Muse Wonder

Change models
Claude Fable 5.1Anthropic
Muse WonderMeta
IndexAll categories, out of 100.
76.2 ±2.4 best
73.1 ±4.0
GapIndex points below the top.
Top
−3.1 · no clear gap
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
69/s
80/s best
EloLMArena rating and rank.
1512 best
1503
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$10.00
$4.00 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$20.00 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
$18.00 best
1K documents20K tokens in, 1K out, each.
$250.00
$100.00 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$1,200.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
71.1
73.0 best
CodingCode writing and repair.
77.7 best
72.3
ReasoningLogic problems and puzzles.
75.8 best
73.1
MultimodalTasks with images and text.
77.9
—
KnowledgeFacts and expert knowledge.
77.2 best
68.6
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
74.3
74.4 best
MathMath problems.
77.0 best
73.5

Benchmarks

54 shared
Only Claude Fable 5.1: 78Only Muse Wonder: 8
Claude Fable 5.1
Muse Wonder
Artificial Analysis Humanity's Last ExamKnowledge
59.1% best3 / 222
50.1%12 / 222
Artificial Analysis Long Context ReasoningReasoning
85.3% best5 / 217
80.7%37 / 217
Critical Physics TasksReasoning
29.7% best12 / 214
28.3%15 / 214
OTIS Mock AIME 2024-2025Math
100.0% best1 / 200
99.4%17 / 200
Artificial Analysis Omniscience AccuracyKnowledge
68.4% best2 / 164
38.0%59 / 164
GDPval-AA normalizedAgentic
62.7%6 / 133
63.5% best5 / 133
Vibe Code Bench v1.1Coding
90.3% best6 / 123
83.1%22 / 123
Artificial Analysis SciCodeCoding
63.1% best3 / 114
60.3%10 / 114
FrontierMath-Tiers-1-3-v2-PrivateMath
90.2% best7 / 90
82.1%18 / 90
Legal Research BenchLegal
55.3% best2 / 90
50.5%7 / 90
Tax Agent BenchFinance
50.7% best2 / 82
36.3%15 / 82
LiveBench Data AnalysisReasoning
80.3%9 / 80
81.6% best5 / 80
LiveBench ReasoningReasoning
91.7% best5 / 80
90.6%11 / 80
Mystery Game PuzzlesReasoning
58.0% best10 / 80
51.0%15 / 80
Finance Agent (v2)Finance
58.9% best8 / 79
56.6%18 / 79
Code MigrationCoding
54.6%11 / 77
62.6% best6 / 77
EMBFinance
76.7% best1 / 75
67.1%18 / 75
FrontierMath-Tier-4-v2-PrivateMath
87.8% best9 / 72
70.7%17 / 72
LiveBench Agentic CodingAgentic
66.1% best3 / 66
62.7%9 / 66
LiveBench CodingCoding
86.4% best3 / 66
80.7%16 / 66