ModelCap

Current AI model comparison

Exact identities · public evidence

DeepSeek

DeepSeek V4 Pro 0813

Position

#30

Index

74.2

Measured

3 public benchmark observations across 3 boards

Comparison side 1

MiniMax

MiniMax M3.1 Flash

Position

#22

Index

77.4

Estimated

publisher-corpus-prior over 211 held-out anchors (6%); launch card against 5 resolved peers on 6 rows (94%); optimism haircut 0 from cross-lab-probe; shrunk 1.9 toward the measured corpus

Comparison side 2

Output / 1M

$1.98

vs $0.60

Context

1M

vs 1M

Weights

Open weights

vs Restricted license