ModelCap
Current AI model comparison
Exact identities · public evidence
DeepSeek
DeepSeek V4.1 Flash
Position
#21
Index
75.1
Measured
2 public benchmark observations across 2 boards
Comparison side 1
Mistral AI
Mistral Medium 3.5
Position
#63
Index
55.9
Measured
4 public benchmark observations across 4 boards
Comparison side 2
Output / 1M
$0.60
vs $7.50
Context
1M
vs 262K
Weights
Open weights
vs API only