ModelCap

Current AI model comparison

Exact identities · public evidence

DeepSeek

R1 0528

Position

#62

Index

63.1

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Dots Studio

Dots3-Note Preview

Position

#70

Index

61.2

Measured

global-corpus-prior over 209 held-out anchors (59%); 1 specialist-board observation at 2.1% support (41%); shrunk 6.3 toward the measured corpus

Comparison side 2

Output / 1M

$2.15

vs Free

Context

164K

vs 512K

Weights

Open weights

vs API only