Inference
EN

Claude Opus 5 vs Muse Wonder Full

Change models
Claude Opus 5Anthropic
Muse Wonder FullMeta
IndexAll categories, out of 100.
73.8 ±1.9
77.3 ±5.3 best
GapIndex points below the top.
−3.5 · no clear gap
Top
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
48/s
—
EloLMArena rating and rank.
1502
—
ReleasedMonth of release.
2026-07
2026-10
Input / 1MUS dollars per 1M input tokens.
$5.00
—
Output / 1MUS dollars per 1M output tokens.
$25.00
—
Batch output / 1MBatch price per 1M output tokens.
$12.50
—
1K chats2K tokens in, 500 out, each.
$22.50
—
1K documents20K tokens in, 1K out, each.
$125.00
—
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
—
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.6
78.2 best
CodingCode writing and repair.
74.8
77.3 best
ReasoningLogic problems and puzzles.
75.4
75.6 best
MultimodalTasks with images and text.
72.5
—
KnowledgeFacts and expert knowledge.
73.1 best
71.7
MultilingualTasks in many languages.
63.6
—
InstructionTasks with strict prompt rules.
55.6
—
MathMath problems.
74.8
79.6 best

Benchmarks

34 shared
Only Claude Opus 5: 116Only Muse Wonder Full: 8
Claude Opus 5
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
54.9% best7 / 222
53.6%9 / 222
Artificial Analysis Long Context ReasoningReasoning
79.3%52 / 217
83.7% best10 / 217
Critical Physics TasksReasoning
29.1%13 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
60.9% best7 / 164
41.0%46 / 164
LegalBenchLegal
87.0%7 / 149
87.4% best4 / 149
GDPval-AA normalizedAgentic
61.1%7 / 133
67.9% best2 / 133
Vibe Code Bench v1.1Coding
88.4% best11 / 123
86.0%14 / 123
Artificial Analysis SciCodeCoding
56.4%26 / 114
62.6% best4 / 114
MedScribeHealthcare
91.0% best4 / 109
89.3%8 / 109
MedCodeHealthcare
63.6% best1 / 106
49.9%18 / 106
Legal Research BenchLegal
55.3% best2 / 90
53.4%6 / 90
Tax Agent BenchFinance
47.1% best5 / 82
43.0%8 / 82
Finance Agent (v2)Finance
58.6%10 / 79
59.1% best6 / 79
Code MigrationCoding
57.5%8 / 77
61.0% best7 / 77
EMBFinance
73.6% best6 / 75
71.9%10 / 75
ProgramBenchCoding
3.0% best6 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
53.5%10 / 61
58.1% best6 / 61
DeepSWEAgentic
68.8%24 / 59
79.0% best1 / 59
Agent Arena steerabilityAgentic
4.417 / 54
9.6 best12 / 54
Agent Arena task outcomeAgentic
10.210 / 54
11.1 best9 / 54