Claude Opus 4 vs DeepSeek V3.2
Change modelsClaude Opus 4Anthropic
DeepSeek V3.2DeepSeek
IndexAll categories, out of 100.
43.9 ±5.3
44.2 ±4.9 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
—
19/s
EloLMArena rating and rank.
1366
1425 best
ReleasedMonth of release.
—
2025-12
Input / 1MUS dollars per 1M input tokens.
—
$0.26
Output / 1MUS dollars per 1M output tokens.
—
$0.38
1K chats2K tokens in, 500 out, each.
—
$0.71
1K documents20K tokens in, 1K out, each.
—
$5.58
1K agent tasks200K tokens in, 20K out, each.
—
$59.60
ContextMaximum tokens in one request.
—
164K
AgenticMulti-step tasks with tools.
49.6 best
43.1
CodingCode writing and repair.
47.3
48.8 best
ReasoningLogic problems and puzzles.
38.6
42.9 best
MultimodalTasks with images and text.
50.6
—
KnowledgeFacts and expert knowledge.
48.2 best
43.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
34.8
MathMath problems.
39.4
46.8 best
Benchmarks
17 sharedOnly Claude Opus 4: 8Only DeepSeek V3.2: 21
Claude Opus 4
DeepSeek V3.2