DeepSeek-R1-0528 vs DeepSeek V3.2
Change modelsDeepSeek-R1-0528DeepSeek
DeepSeek V3.2DeepSeek
IndexAll categories, out of 100.
44.4 ±8.9 best
44.3 ±4.9
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
60%
85% best
SpeedOutput tokens per second.
34/s
36/s best
EloLMArena rating and rank.
1428 best
1425
ReleasedMonth of release.
2025-05
2025-12
Input / 1MUS dollars per 1M input tokens.
$0.571
$0.26 best
Output / 1MUS dollars per 1M output tokens.
$2.29
$0.38 best
1K chats2K tokens in, 500 out, each.
$2.29
$0.71 best
1K documents20K tokens in, 1K out, each.
$13.71
$5.58 best
1K agent tasks200K tokens in, 20K out, each.
$159.92
$59.60 best
ContextMaximum tokens in one request.
164K
164K
AgenticMulti-step tasks with tools.
—
44.2
CodingCode writing and repair.
46.5
48.3 best
ReasoningLogic problems and puzzles.
38.0
42.5 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
45.6 best
43.4
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
34.9
MathMath problems.
46.2
46.4 best
Benchmarks
4 sharedOnly DeepSeek-R1-0528: 9Only DeepSeek V3.2: 34
DeepSeek-R1-0528
DeepSeek V3.2