DeepSeek-R1 vs dots3-note Preview
Change modelsDeepSeek-R1DeepSeek
dots3-note PreviewDots Studio
IndexAll categories, out of 100.
38.9 ±5.0
63.4 ±3.9 best
GapIndex points below the top.
−24.5
Top
CoverageIndex weight that has results.
85%
95% best
SpeedOutput tokens per second.
18/s
—
EloLMArena rating and rank.
1373
—
ReleasedMonth of release.
2025-01
2026-08
Input / 1MUS dollars per 1M input tokens.
$0.70
Free best
Output / 1MUS dollars per 1M output tokens.
$2.50
Free best
1K chats2K tokens in, 500 out, each.
$2.65
Free best
1K documents20K tokens in, 1K out, each.
$16.50
Free best
1K agent tasks200K tokens in, 20K out, each.
$190.00
Free best
ContextMaximum tokens in one request.
64K
512K best
AgenticMulti-step tasks with tools.
27.6
63.3 best
CodingCode writing and repair.
42.6
60.3 best
ReasoningLogic problems and puzzles.
39.8
74.5 best
MultimodalTasks with images and text.
—
59.2
KnowledgeFacts and expert knowledge.
43.5
77.2 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
28.5
58.2 best
MathMath problems.
43.8
62.3 best
Benchmarks
3 sharedOnly DeepSeek-R1: 31Only dots3-note Preview: 24
DeepSeek-R1
dots3-note Preview