Claude 3 Haiku vs Claude 3 Opus
Change modelsClaude 3 HaikuAnthropic
Claude 3 OpusAnthropic
IndexAll categories, out of 100.
22.0 ±5.4
23.3 ±9.7 best
GapIndex points below the top.
−1.3 · no clear gap
Top
CoverageIndex weight that has results.
95% best
60%
SpeedOutput tokens per second.
73/s
—
EloLMArena rating and rank.
1195
1262 best
ReleasedMonth of release.
2024-03
2024-03
Input / 1MUS dollars per 1M input tokens.
$0.25 best
$15.00
Output / 1MUS dollars per 1M output tokens.
$1.25 best
$75.00
1K chats2K tokens in, 500 out, each.
$1.13 best
$67.50
1K documents20K tokens in, 1K out, each.
$6.25 best
$375.00
1K agent tasks200K tokens in, 20K out, each.
$75.00 best
$4,500.00
ContextMaximum tokens in one request.
200K
200K
AgenticMulti-step tasks with tools.
16.8
—
CodingCode writing and repair.
31.2 best
9.5
ReasoningLogic problems and puzzles.
31.6
37.0 best
MultimodalTasks with images and text.
5.0
—
KnowledgeFacts and expert knowledge.
24.1
27.6 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
22.8
—
MathMath problems.
8.1
14.4 best
Benchmarks
6 sharedOnly Claude 3 Haiku: 6Only Claude 3 Opus: 6
Claude 3 Haiku
Claude 3 Opus