ModelCap

Current AI model comparison

Exact identities · public evidence

DeepSeek

DeepSeek V3.1 Terminus

Position

#69

Index

58.9

Measured

3 public benchmark observations across 3 boards

Comparison side 1

Dots Studio

Dots3-Note Preview

Position

#68

Index

59.3

Measured

global-corpus-prior over 203 held-out anchors (60%); 1 specialist-board observation at 2.1% support (40%); shrunk 6.6 toward the measured corpus

Comparison side 2

Output / 1M

$1.00

vs Free

Context

164K

vs 512K

Weights

Open weights

vs API only