ModelCap

Current AI model comparison

Exact identities · public evidence

IFM

K2 Horizon 375B A23B

Position

#30

Index

67.3

Estimated

global-corpus-prior over 186 held-out anchors (21%); launch card against 6 resolved peers on 11 rows (79%); optimism haircut 0 from cross-lab-probe; shrunk 4.1 toward the measured corpus

Comparison side 1

Tencent

Hy4 preview

Position

#25

Index

70.8

Measured

9 reported rows against measured corpus ladders (41%); publisher-corpus-prior over 186 held-out anchors (12%); opens above measured predecessor tencent/hy3 on same-family ordering evidence (39%); 1 specialist-board observation at 2.5% support (9%); shrunk 1.3 toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs $2.50

Context

vs 1M

Weights

Open weights

vs Open weights