ModelCap

Current AI model comparison

Exact identities · public evidence

Amazon

Nova Micro 1.0

Position

#214

Index

14.3

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Microsoft

Phi 3.5 MoE instruct

Position

#218

Index

12.8

Estimated

publisher-corpus-prior over 215 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 4.2 toward the measured corpus

Comparison side 2

Output / 1M

$0.14

vs Unavailable

Context

128K

vs

Weights

API only

vs Open weights