Claude Fable 5 vs Claude Fable 5.2

Change models
Claude Fable 5.2AnthropicSmartest
IndexAll categories, out of 100.
74.0 ±2.7
85.6 ±3.7 best
GapIndex points below the top.
−11.6
Top
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
56/s
64/s best
EloLMArena rating and rank.
1492
—
ReleasedMonth of release.
2026-06
2026-11
Input / 1MUS dollars per 1M input tokens.
$10.00
$8.00 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$40.00 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
$20.00 best
1K chats2K tokens in, 500 out, each.
$45.00
$36.00 best
1K documents20K tokens in, 1K out, each.
$250.00
$200.00 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$2,400.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.4
82.2 best
CodingCode writing and repair.
74.7
86.2 best
ReasoningLogic problems and puzzles.
73.6
86.5 best
MultimodalTasks with images and text.
70.1
82.0 best
KnowledgeFacts and expert knowledge.
75.8
87.1 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
64.1
—
MathMath problems.
76.2
79.3 best

Benchmarks

30 shared
Only Claude Fable 5: 62Only Claude Fable 5.2: 41
Claude Fable 5
Claude Fable 5.2
55.5%5 / 222
74.3% best1 / 222
82.3%27 / 217
83.3% best13 / 217
85.9%69 / 217
93.9% best14 / 217
28.6%14 / 214
35.4% best1 / 214
99.7%14 / 200
99.7%14 / 200
65.4%4 / 164
79.1% best1 / 164
89.2%11 / 131
92.5% best3 / 131
98.5% best1 / 126
97.5%5 / 126
90.4%4 / 123
93.8% best1 / 123
96.4%9 / 122
98.8% best1 / 122
97.6%17 / 116
99.0% best2 / 116
61.0%6 / 114
67.7% best1 / 114
70.7%9 / 91
94.0% best1 / 91
Chess PuzzlesReasoning
47.0%24 / 90
79.0% best1 / 90
87.0%12 / 90
95.1% best1 / 90
49.5% best9 / 90
46.2%19 / 90
80.0%6 / 83
93.0% best1 / 83
38.3% best12 / 82
32.1%23 / 82
52.0%14 / 80
90.0% best1 / 80
90.2%7 / 72
100.0% best1 / 72