ModelCap

Current AI model comparison

Exact identities · public evidence

Meta

Llama 4 Maverick

Position

#167

Index

32.2

Measured

3 public benchmark observations across 3 boards

Comparison side 1

Microsoft

Phi 3.5 MoE instruct

Position

#165

Index

33.6

Estimated

global-corpus-prior over 209 held-out anchors (42%); launch card against 4 resolved peers on 6 rows (58%); exceeds every named peer on 4 of 6 rows; optimism haircut 0.67 from cross-lab-probe; shrunk 16.7 up toward the measured corpus

Comparison side 2

Output / 1M

$0.652

vs Unavailable

Context

1M

vs

Weights

Gated access

vs Open weights