Claude Haiku 4.5 Thinking vs Claude Sonnet 4.5
Change modelsClaude Haiku 4.5 ThinkingAnthropic
Claude Sonnet 4.5Anthropic
IndexAll categories, out of 100.
43.5 ±7.0
47.9 ±5.5 best
GapIndex points below the top.
−4.4 · no clear gap
Top
CoverageIndex weight that has results.
75%
80% best
SpeedOutput tokens per second.
—
45/s
EloLMArena rating and rank.
—
1439
ReleasedMonth of release.
2025-10
2025-09
Input / 1MUS dollars per 1M input tokens.
—
$3.00
Output / 1MUS dollars per 1M output tokens.
—
$15.00
Batch output / 1MBatch price per 1M output tokens.
—
$7.50
1K chats2K tokens in, 500 out, each.
—
$13.50
1K documents20K tokens in, 1K out, each.
—
$75.00
1K agent tasks200K tokens in, 20K out, each.
—
$900.00
ContextMaximum tokens in one request.
200K
1M best
AgenticMulti-step tasks with tools.
50.2 best
49.3
CodingCode writing and repair.
42.5
53.9 best
ReasoningLogic problems and puzzles.
—
45.3
MultimodalTasks with images and text.
30.1
—
KnowledgeFacts and expert knowledge.
43.6
49.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
51.6 best
46.6
Benchmarks
3 sharedOnly Claude Haiku 4.5 Thinking: 25Only Claude Sonnet 4.5: 32
Claude Haiku 4.5 Thinking
Claude Sonnet 4.5