Claude 3 Opus vs Phi-4
Change modelsClaude 3 OpusAnthropic
Phi-4Microsoft
IndexAll categories, out of 100.
23.3 ±9.7 best
22.4 ±5.7
GapIndex points below the top.
Top
−0.9 · no clear gap
CoverageIndex weight that has results.
60%
90% best
SpeedOutput tokens per second.
—
93/s
EloLMArena rating and rank.
1262 best
1217
ReleasedMonth of release.
2024-03
2024-12
Input / 1MUS dollars per 1M input tokens.
$15.00
$0.07 best
Output / 1MUS dollars per 1M output tokens.
$75.00
$0.14 best
1K chats2K tokens in, 500 out, each.
$67.50
$0.21 best
1K documents20K tokens in, 1K out, each.
$375.00
$1.54 best
1K agent tasks200K tokens in, 20K out, each.
$4,500.00
$16.80 best
ContextMaximum tokens in one request.
200K best
16K
AgenticMulti-step tasks with tools.
—
5.0
CodingCode writing and repair.
9.5
23.4 best
ReasoningLogic problems and puzzles.
37.0 best
22.1
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
27.6
29.9 best
MultilingualTasks in many languages.
—
24.0
InstructionTasks with strict prompt rules.
—
11.0
MathMath problems.
14.4
23.7 best
Benchmarks
5 sharedOnly Claude 3 Opus: 7Only Phi-4: 9
Claude 3 Opus
Phi-4