ModelCap

Current AI model comparison

Exact identities · public evidence

Google

Gemini 3.1 Pro Preview

Position

#12

Index

77.8

Measured

4 public benchmark observations across 4 boards

Comparison side 1

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 2

Output / 1M

$12.00

vs Unavailable

Context

1M

vs —

Weights

API only

vs Open weights