ModelCap
Current AI model comparison
Exact identities · public evidence
Gemini 4 Argon
Position
#33
Index
73.0
Estimated
1 reported rows against measured corpus ladders (72%); publisher-corpus-prior over 211 held-out anchors (28%); shrunk 3.7 toward the measured corpus
Comparison side 1
Moonshot AI
Kimi K3
Position
#9
Index
82.0
Measured
5 public benchmark observations across 5 boards
Comparison side 2
Output / 1M
$10.00
vs $10.00
Context
1M
vs 1M
Weights
No linked weights
vs Restricted license