Gemini 3 Pro vs Kimi K2.6

Change models
Kimi K2.6Moonshot AI
IndexAll categories, out of 100.
57.9 ±2.7
58.2 ±2.9 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
109/s best
81/s
EloLMArena rating and rank.
1480 best
1455
ReleasedMonth of release.
2025-11
2026-04
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.65 best
Output / 1MUS dollars per 1M output tokens.
$12.00
$3.41 best
1K chats2K tokens in, 500 out, each.
$10.00
$3.01 best
1K documents20K tokens in, 1K out, each.
$52.00
$16.41 best
1K agent tasks200K tokens in, 20K out, each.
$640.00
$198.20 best
ContextMaximum tokens in one request.
2M best
262K
AgenticMulti-step tasks with tools.
56.2
59.5 best
CodingCode writing and repair.
56.4
59.3 best
ReasoningLogic problems and puzzles.
57.2 best
53.8
MultimodalTasks with images and text.
54.8
57.6 best
KnowledgeFacts and expert knowledge.
66.1 best
56.1
MultilingualTasks in many languages.
60.1
—
InstructionTasks with strict prompt rules.
54.8
60.0 best
MathMath problems.
58.2
60.0 best

Benchmarks

34 shared
Only Gemini 3 Pro: 41Only Kimi K2.6: 42
Gemini 3 Pro
Kimi K2.6
39.7% best48 / 222
37.5%57 / 222
76.0%88 / 217
81.0% best35 / 217
92.6% best27 / 217
90.8%37 / 217
9.1% best70 / 214
8.0%75 / 214
91.4%56 / 200
96.1% best37 / 200
90.8%30 / 199
91.1% best27 / 199
55.8% best11 / 164
32.6%72 / 164
87.0% best7 / 149
84.7%30 / 149
87.1%48 / 149
95.9% best13 / 149
70.4%42 / 146
76.0% best15 / 146
TaxEval v2Finance
72.6%60 / 143
74.7% best31 / 143
86.4%23 / 142
86.8% best20 / 142
91.7% best18 / 135
89.1%31 / 135
MMLU ProKnowledge
90.1% best6 / 135
87.6%25 / 135
CorpFin v2Finance
63.7%40 / 131
66.7% best16 / 131
14.3%99 / 123
37.9% best76 / 123
80.2% best22 / 113
79.4%26 / 113
MedScribeHealthcare
72.0%91 / 109
78.1% best67 / 109
MedCodeHealthcare
52.2% best14 / 106
40.1%68 / 106
69.1% best7 / 97
65.8%39 / 97