Claude 3.5 Haiku vs Claude 3 Opus
Change modelsClaude 3.5 HaikuAnthropic
Claude 3 OpusAnthropic
IndexAll categories, out of 100.
24.1 ±3.4 best
23.3 ±9.7
GapIndex points below the top.
Top
−0.8 · no clear gap
CoverageIndex weight that has results.
100% best
60%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
1255
1262 best
ReleasedMonth of release.
2024-10
2024-03
Input / 1MUS dollars per 1M input tokens.
—
$15.00
Output / 1MUS dollars per 1M output tokens.
—
$75.00
1K chats2K tokens in, 500 out, each.
—
$67.50
1K documents20K tokens in, 1K out, each.
—
$375.00
1K agent tasks200K tokens in, 20K out, each.
—
$4,500.00
ContextMaximum tokens in one request.
200K
200K
AgenticMulti-step tasks with tools.
26.6
—
CodingCode writing and repair.
28.0 best
9.5
ReasoningLogic problems and puzzles.
31.4
37.0 best
MultimodalTasks with images and text.
14.5
—
KnowledgeFacts and expert knowledge.
24.4
27.6 best
MultilingualTasks in many languages.
31.1
—
InstructionTasks with strict prompt rules.
32.6
—
MathMath problems.
16.2 best
14.4
Benchmarks
5 sharedOnly Claude 3.5 Haiku: 28Only Claude 3 Opus: 7
Claude 3.5 Haiku
Claude 3 Opus