Claude 3.5 Haiku vs Claude 3.5 Sonnet
Change modelsClaude 3.5 HaikuAnthropic
Claude 3.5 SonnetAnthropic
IndexAll categories, out of 100.
24.1 ±3.4
32.2 ±9.2 best
GapIndex points below the top.
−8.1 · no clear gap
Top
CoverageIndex weight that has results.
100% best
55%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
1255
1298 best
ReleasedMonth of release.
2024-10
2024-06
Input / 1MUS dollars per 1M input tokens.
—
$3.00
Output / 1MUS dollars per 1M output tokens.
—
$15.00
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
200K
AgenticMulti-step tasks with tools.
26.6
—
CodingCode writing and repair.
28.0
34.0 best
ReasoningLogic problems and puzzles.
31.4
—
MultimodalTasks with images and text.
14.5
44.7 best
KnowledgeFacts and expert knowledge.
24.4
37.4 best
MultilingualTasks in many languages.
31.1
—
InstructionTasks with strict prompt rules.
32.6
—
MathMath problems.
16.2
25.2 best
Benchmarks
15 sharedOnly Claude 3.5 Haiku: 18Only Claude 3.5 Sonnet: 12
Claude 3.5 Haiku
Claude 3.5 Sonnet