Gemini 3 Flash Preview vs Kimi K2.7 Code

Change models
Kimi K2.7 CodeMoonshot AI
IndexAll categories, out of 100.
57.3 ±5.3
57.5 ±4.5 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
84/s best
55/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-12
2026-06
Input / 1MUS dollars per 1M input tokens.
$0.50 best
$0.60
Output / 1MUS dollars per 1M output tokens.
$3.00 best
$3.50
Batch output / 1MBatch price per 1M output tokens.
$1.50
—
1K chats2K tokens in, 500 out, each.
$2.50 best
$2.95
1K documents20K tokens in, 1K out, each.
$13.00 best
$15.50
1K agent tasks200K tokens in, 20K out, each.
$160.00 best
$190.00
ContextMaximum tokens in one request.
1.05M best
262K
AgenticMulti-step tasks with tools.
57.0
58.1 best
CodingCode writing and repair.
54.8
60.3 best
ReasoningLogic problems and puzzles.
60.0 best
54.3
MultimodalTasks with images and text.
68.9
—
KnowledgeFacts and expert knowledge.
56.7
58.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
44.2
MathMath problems.
57.0 best
56.7

Benchmarks

6 shared
Only Gemini 3 Flash Preview: 26Only Kimi K2.7 Code: 31
Gemini 3 Flash Preview
Kimi K2.7 Code
85.6% best29 / 142
82.0%57 / 142
20.2%92 / 125
47.2% best75 / 125
SWE-benchCoding
75.0%44 / 87
78.2% best30 / 87
6.4%69 / 77
25.4% best48 / 77
53.9%53 / 75
67.0% best36 / 75
0.0%34 / 65
0.0%34 / 65