ModelCap

Current AI model comparison

Exact identities · public evidence

IFM

K2 Horizon MoVA 36B A4B

Position

#68

Index

53.3

Estimated

global-corpus-prior over 186 held-out anchors (79%); launch card against 3 resolved peers on 8 rows (21%); exceeds every named peer on 4 of 8 rows; optimism haircut 2.24 from cross-lab-probe; shrunk 3.9 toward the measured corpus

Comparison side 1

Tencent

UI Mate democua 27B

Position

#72

Index

52.6

Inherited

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

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Open weights