Command A+ vs Kimi K2

Change models
Command A+Cohere
Kimi K2Moonshot AI
IndexAll categories, out of 100.
40.2 ±6.0 best
39.5 ±5.4
GapIndex points below the top.
Top
−0.7 · no clear gap
CoverageIndex weight that has results.
85%
85%
SpeedOutput tokens per second.
237/s best
42/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-05
2025-07
Input / 1MUS dollars per 1M input tokens.
$0.30 best
$0.57
Output / 1MUS dollars per 1M output tokens.
$1.50 best
$2.30
1K chats2K tokens in, 500 out, each.
$1.35 best
$2.29
1K documents20K tokens in, 1K out, each.
$7.50 best
$13.70
1K agent tasks200K tokens in, 20K out, each.
$90.00 best
$160.00
ContextMaximum tokens in one request.
192K best
131K
AgenticMulti-step tasks with tools.
41.7
45.6 best
CodingCode writing and repair.
45.6 best
38.7
ReasoningLogic problems and puzzles.
40.2 best
40.0
MultimodalTasks with images and text.
34.7
—
KnowledgeFacts and expert knowledge.
36.1
41.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
57.2 best
36.0
MathMath problems.
—
35.8

Benchmarks

7 shared
Only Command A+: 11Only Kimi K2: 18
Command A+
Kimi K2
12.0% best129 / 216
7.4%152 / 216
52.7%145 / 211
53.0% best142 / 211
0.3% best132 / 207
0.0%145 / 207
76.1%107 / 193
76.6% best104 / 193
9.8%166 / 170
27.4% best91 / 170
85.0% best54 / 143
61.1%80 / 143
73.9% best25 / 140
41.5%93 / 140