GitHub[208K]Try OpenCode

Compare AI models: Kimi K2.7 Code vs mai-experimental-test

  1. Kimi K2.7 CodeMoonshotHollow points use fallbacks · hover for details
  2. mai-experimental-testHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2.7 Code50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder37/10061/10050/10050/100 — Tool calling supported; no comparable benchmark
mai-experimental-test50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder
Overview
Author
Context length
262K
Unknown
Reasoning
True
Unknown
Input modalities
Text, Image, Video
Unknown
Output modalities
Text
Unknown
Providers
Pricing
Input
$0.95/ 1M
Unknown
Output
$4.00/ 1M
Unknown
Cached input
$0.19/ 1M
Unknown
MomentumLast 2 mo
Unique users
233K
56K
Completed sessions
428,760
585,872
Token share
0.17%
0.03%
Tokens
1.5T-54%
273B+100%
AUG 8OCT 2
AUG 8OCT 2
RetentionWeek 1
Returning users
55%19K user-weeks
Pending

Related comparisons. Other model pairs to check.