Claude Sonnet 4 vs Claude Haiku 4.5
Change modelsClaude Sonnet 4Anthropic
Claude Haiku 4.5Anthropic
IndexAll categories, out of 100.
43.0 ±5.2
43.2 ±4.2 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
90%
95% best
SpeedOutput tokens per second.
49/s
88/s best
EloLMArena rating and rank.
1339
1397 best
ReleasedMonth of release.
2025-05
2025-10
Input / 1MUS dollars per 1M input tokens.
$3.00
$1.00 best
Output / 1MUS dollars per 1M output tokens.
$15.00
$5.00 best
Batch output / 1MBatch price per 1M output tokens.
—
$2.50
1K chats2K tokens in, 500 out, each.
$13.50
$4.50 best
1K documents20K tokens in, 1K out, each.
$75.00
$25.00 best
1K agent tasks200K tokens in, 20K out, each.
$900.00
$300.00 best
ContextMaximum tokens in one request.
200K
200K
AgenticMulti-step tasks with tools.
49.4 best
48.9
CodingCode writing and repair.
46.2
49.9 best
ReasoningLogic problems and puzzles.
38.9 best
38.1
MultimodalTasks with images and text.
49.4 best
42.6
KnowledgeFacts and expert knowledge.
44.5 best
36.1
MultilingualTasks in many languages.
—
44.5
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
38.9
40.5 best
Benchmarks
12 sharedOnly Claude Sonnet 4: 18Only Claude Haiku 4.5: 26
Claude Sonnet 4
Claude Haiku 4.5