DeepSeek-R1 vs DeepSeek V3 0324
Change modelsDeepSeek-R1DeepSeek
DeepSeek V3 0324DeepSeek
IndexAll categories, out of 100.
38.9 ±5.0 best
37.1 ±5.0
GapIndex points below the top.
Top
−1.8 · no clear gap
CoverageIndex weight that has results.
85%
90% best
SpeedOutput tokens per second.
18/s
—
EloLMArena rating and rank.
1373
1375 best
ReleasedMonth of release.
2025-01
2025-03
Input / 1MUS dollars per 1M input tokens.
$0.70
—
Output / 1MUS dollars per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$2.65
—
1K documents20K tokens in, 1K out, each.
$16.50
—
1K agent tasks200K tokens in, 20K out, each.
$190.00
—
ContextMaximum tokens in one request.
64K
128K best
AgenticMulti-step tasks with tools.
27.6
34.0 best
CodingCode writing and repair.
42.6 best
40.9
ReasoningLogic problems and puzzles.
39.8 best
36.0
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
43.5 best
37.6
MultilingualTasks in many languages.
—
40.1
InstructionTasks with strict prompt rules.
28.5 best
27.3
MathMath problems.
43.8 best
38.0
Benchmarks
16 sharedOnly DeepSeek-R1: 18Only DeepSeek V3 0324: 6
DeepSeek-R1
DeepSeek V3 0324