ModelCap

Current AI model comparison

Exact identities · public evidence

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 1

Tencent

UI Mate democua 27B

Position

#66

Index

60.1

Inherited

finetune of qwen/qwen3.6-27b · finetune (100%)

Comparison side 2

Output / 1M

Free

vs Unavailable

Context

512K

vs —

Weights

API only

vs Open weights