GitHub[220K]Try OpenCode

Compare AI models: gemini-4-argon-contributor vs Kimi K2.7 Code

  1. gemini-4-argon-contributorGoogleHollow 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
gemini-4-argon-contributor50/100 — 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
Kimi K2.7 Code50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder34/10063/10050/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
Unknown
262K
Reasoning
Unknown
True
Input modalities
Unknown
Text, Image, Video
Output modalities
Unknown
Text
Providers
Pricing
Input
Unknown
$0.67/ 1M
Output
Unknown
$3.35/ 1M
Cached input
Unknown
$0.15/ 1M
MomentumLast 2 mo
Unique users
32K
160K
Completed sessions
137,475
570,933
Token share
0.03%
0.11%
Tokens
309B+100%
1.3T-47%
SEP 1OCT 26
SEP 1OCT 26
RetentionWeek 1
Returning users
61.5%1.4K user-weeks
57.2%14K user-weeks

Related comparisons. Other model pairs to check.