Claude Fable 5.2 vs Muse Wonder Full

Change models
Claude Fable 5.2AnthropicSmartest
IndexAll categories, out of 100.
85.6 ±3.7 best
77.3 ±5.3
GapIndex points below the top.
Top
−8.3
CoverageIndex weight that has results.
90% best
80%
SpeedOutput tokens per second.
64/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-11
2026-10
Input / 1MUS dollars per 1M input tokens.
$8.00
—
Output / 1MUS dollars per 1M output tokens.
$40.00
—
Batch output / 1MBatch price per 1M output tokens.
$20.00
—
1K chats2K tokens in, 500 out, each.
$36.00
—
1K documents20K tokens in, 1K out, each.
$200.00
—
1K agent tasks200K tokens in, 20K out, each.
$2,400.00
—
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
82.2 best
78.2
CodingCode writing and repair.
86.2 best
77.3
ReasoningLogic problems and puzzles.
86.5 best
75.6
MultimodalTasks with images and text.
82.0
—
KnowledgeFacts and expert knowledge.
87.1 best
71.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
79.3
79.6 best

Benchmarks

25 shared
Only Claude Fable 5.2: 46Only Muse Wonder Full: 17
Claude Fable 5.2
Muse Wonder Full
74.3% best1 / 222
53.6%9 / 222
83.3%13 / 217
83.7% best10 / 217
35.4% best1 / 214
32.9%2 / 214
79.1% best1 / 164
41.0%46 / 164
93.8% best1 / 123
86.0%14 / 123
67.7% best1 / 114
62.6%4 / 114
46.2%19 / 90
53.4% best6 / 90
32.1%23 / 82
43.0% best8 / 82
19.0% best1 / 65
0.5%19 / 65
65.2% best1 / 61
58.1%6 / 61
DeepSWEAgentic
74.3%9 / 59
79.0% best1 / 59
33.0 best1 / 54
9.612 / 54
22.0 best1 / 54
11.19 / 54
100.0% best1 / 54
94.0%11 / 54
55.7% best2 / 44
37.1%8 / 44
5.0%27 / 35
23.3% best5 / 35
83.7% best1 / 30
73.3%9 / 30
51.8% best2 / 30
35.1%11 / 30
58.0% best1 / 25
42.0%6 / 25
76.4% best3 / 23
45.4%21 / 23