Claude Fable 5.2 vs Claude Haiku 5.5
Change models
Claude Haiku 5.5Anthropic
IndexAll categories, out of 100.
85.6 ±3.7 best
66.3 ±2.8
GapIndex points below the top.
Top
−19.3
CoverageIndex weight that has results.
90%
95% best
SpeedOutput tokens per second.
64/s
159/s best
EloLMArena rating and rank.
—
1399
ReleasedMonth of release.
2026-11
2026-10
Input / 1MUS dollars per 1M input tokens.
$8.00
$0.10 best
Output / 1MUS dollars per 1M output tokens.
$40.00
$0.50 best
Batch output / 1MBatch price per 1M output tokens.
$20.00
$0.25 best
1K chats2K tokens in, 500 out, each.
$36.00
$0.45 best
1K documents20K tokens in, 1K out, each.
$200.00
$2.50 best
1K agent tasks200K tokens in, 20K out, each.
$2,400.00
$30.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
82.2 best
68.6
CodingCode writing and repair.
86.2 best
71.0
ReasoningLogic problems and puzzles.
86.5 best
67.8
MultimodalTasks with images and text.
82.0 best
51.9
KnowledgeFacts and expert knowledge.
87.1 best
54.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
37.2
MathMath problems.
79.3 best
68.3
Benchmarks
47 sharedOnly Claude Fable 5.2: 24Only Claude Haiku 5.5: 37
Claude Fable 5.2
Claude Haiku 5.5