ModelCap
Current AI model comparison
Exact identities · public evidence
DeepSeek
DeepSeek V4.1 Flash
Position
#11
Index
79.4
Measured
4 public benchmark observations across 4 boards
Comparison side 1
Gemini 3.5 Flash Lite
Position
#28
Index
71.5
Measured
4 public benchmark observations across 4 boards
Comparison side 2
Output / 1M
$0.60
vs $2.50
Context
1M
vs 1M
Weights
Open weights
vs API only