Kimi K2.5 vs Kimi K2.5 (Reasoning)
Change modelsKimi K2.5Moonshot AI
Kimi K2.5 (Reasoning)Moonshot AI
IndexAll categories, out of 100.
52.2 ±2.2
53.0 ±4.0 best
GapIndex points below the top.
−0.8 · no clear gap
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
36/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-01
2026-01
Input / 1MUS dollars per 1M input tokens.
$0.532 best
$0.60
Output / 1MUS dollars per 1M output tokens.
$3.32
$3.00 best
1K chats2K tokens in, 500 out, each.
$2.73
$2.70 best
1K documents20K tokens in, 1K out, each.
$13.97 best
$15.00
1K agent tasks200K tokens in, 20K out, each.
$172.90 best
$180.00
ContextMaximum tokens in one request.
262K best
128K
AgenticMulti-step tasks with tools.
49.4
50.6 best
CodingCode writing and repair.
53.9
56.0 best
ReasoningLogic problems and puzzles.
51.6
52.1 best
MultimodalTasks with images and text.
52.4
53.9 best
KnowledgeFacts and expert knowledge.
53.7
55.5 best
MultilingualTasks in many languages.
52.7
—
InstructionTasks with strict prompt rules.
53.5
54.6 best
MathMath problems.
53.8 best
52.2
Benchmarks
23 sharedOnly Kimi K2.5: 66
Kimi K2.5
Kimi K2.5 (Reasoning)