ModelCap

Current AI model comparison

Exact identities · public evidence

Inception Labs

Mercury 2.5

Position

#116

Index

37.1

Estimated

global-corpus-prior over 183 held-out anchors (22%); opens from measured predecessor inception/mercury-2 (79%); shrunk 4.5 up toward the measured corpus

Comparison side 1

Microsoft

Fara1.5 4B

Position

#114

Index

37.1

Inherited

finetune of Qwen/Qwen3.5-4B · finetune (100%)

Comparison side 2

Output / 1M

$0.15

vs Unavailable

Context

260K

vs —

Weights

API only

vs Open weights