dots3-note Preview vs Kimi K2.5 (Reasoning)
Change modelsdots3-note PreviewDots Studio
Kimi K2.5 (Reasoning)Moonshot AI
IndexAll categories, out of 100.
63.4 ±3.9 best
53.0 ±4.0
GapIndex points below the top.
Top
−10.4
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-08
2026-01
Input / 1MUS dollars per 1M input tokens.
Free best
$0.60
Output / 1MUS dollars per 1M output tokens.
Free best
$3.00
1K chats2K tokens in, 500 out, each.
Free best
$2.70
1K documents20K tokens in, 1K out, each.
Free best
$15.00
1K agent tasks200K tokens in, 20K out, each.
Free best
$180.00
ContextMaximum tokens in one request.
512K best
128K
AgenticMulti-step tasks with tools.
63.3 best
50.6
CodingCode writing and repair.
60.3 best
56.0
ReasoningLogic problems and puzzles.
74.5 best
52.1
MultimodalTasks with images and text.
59.2 best
53.9
KnowledgeFacts and expert knowledge.
77.2 best
55.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
58.2 best
54.6
MathMath problems.
62.3 best
52.2
Benchmarks
4 sharedOnly dots3-note Preview: 23Only Kimi K2.5 (Reasoning): 19
dots3-note Preview
Kimi K2.5 (Reasoning)