Grok 4.6 vs Kimi K3

Change models
Kimi K3Moonshot AI
IndexAll categories, out of 100.
67.4 ±3.7 best
66.6 ±2.4
GapIndex points below the top.
Top
−0.8 · no clear gap
CoverageIndex weight that has results.
85%
95% best
SpeedOutput tokens per second.
70/s best
43/s
EloLMArena rating and rank.
1430
1475 best
ReleasedMonth of release.
2026-08
2026-07
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.192 best
Output / 1MUS dollars per 1M output tokens.
$6.00 best
$16.00
Batch output / 1MBatch price per 1M output tokens.
$4.80 best
$11.40
1K chats2K tokens in, 500 out, each.
$7.00 best
$8.38
1K documents20K tokens in, 1K out, each.
$46.00
$19.84 best
1K agent tasks200K tokens in, 20K out, each.
$520.00
$358.40 best
ContextMaximum tokens in one request.
500K
1.05M best
AgenticMulti-step tasks with tools.
68.0 best
65.7
CodingCode writing and repair.
67.2 best
66.0
ReasoningLogic problems and puzzles.
65.7
67.3 best
MultimodalTasks with images and text.
—
65.3
KnowledgeFacts and expert knowledge.
65.3
66.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
71.6 best
70.6
MathMath problems.
65.0
66.2 best

Benchmarks

74 shared
Only Grok 4.6: 10Only Kimi K3: 56
Grok 4.6
Kimi K3
42.9%34 / 222
46.9% best22 / 222
80.3%40 / 217
88.7% best1 / 217
93.2% best21 / 217
93.1%22 / 217
17.1%42 / 214
23.4% best23 / 214
99.2% best19 / 200
97.2%34 / 200
94.9% best3 / 199
93.5%8 / 199
48.2% best28 / 167
47.6%29 / 167
86.3% best14 / 149
86.2%15 / 149
TaxEval v2Finance
71.1%83 / 143
75.7% best12 / 143
88.2% best7 / 142
87.2%18 / 142
94.7% best3 / 135
92.9%12 / 135
MMLU ProKnowledge
89.4% best11 / 135
88.0%22 / 135
55.9% best16 / 133
51.6%26 / 133
67.1% best31 / 131
60.4%40 / 131
CorpFin v2Finance
66.2%20 / 131
71.6% best3 / 131
87.0%45 / 126
94.5% best21 / 126
76.2%43 / 125
85.0% best19 / 125
68.3% best28 / 122
61.7%37 / 122
96.3% best26 / 116
94.9%34 / 116
56.5%24 / 114
59.5% best11 / 114