ModelCap

Current AI model comparison

Exact identities · public evidence

Moonshot AI

Kimi K2.7 Code

Position

#52

Index

59.1

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Ornith Ai

Ornith 1.5 9B

Position

#58

Index

57.4

Estimated

global-corpus-prior over 186 held-out anchors (47%); launch card against 2 resolved peers on 10 rows (53%); exceeds every named peer on 3 of 10 rows; optimism haircut 0 from cross-lab-probe; shrunk 4.5 toward the measured corpus

Comparison side 2

Output / 1M

$3.50

vs Unavailable

Context

262K

vs

Weights

Restricted license

vs Open weights