Try OpenCodeTry OpenCode

Compare AI models: MiniMax-M3 vs Kimi K2.7 Code

  1. MiniMax-M3MiniMaxHollow points use fallbacks · hover for details
  2. Kimi K2.7 CodeMoonshotHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
MiniMax-M350/100 — Reasoning supported; no comparable benchmark84/10062/10092/10050/10021/100
Kimi K2.7 Code50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder31/10062/10050/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.23/ 1M
$1.00/ 1M
Output
$0.96/ 1M
$4.22/ 1M
Cached input
$0.05/ 1M
Unknown
MomentumLast 2 mo
Unique users
160K
150K
Completed sessions
1,275,876
581,881
Token share
0.14%
0.09%
Tokens
2.1T-39%
1.3T-26%
SEP 22NOV 16
SEP 22NOV 16
RetentionWeek 1
Returning users
67.5%8K user-weeks
63.7%11K user-weeks

Related comparisons. Other model pairs to check.