ModelCap

Current AI model comparison

Exact identities · public evidence

Amazon

GKA primed HQwen3 32B Instruct

Position

#128

Index

32.7

Inherited

finetune of qwen/qwen3-32b · finetune (100%)

Comparison side 1

Cohere

North Mini Code

Position

#123

Index

33.9

Estimated

3 reported rows against measured corpus ladders (59%); publisher-corpus-prior over 183 held-out anchors (41%); shrunk 13.5 toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Free

Context

—

vs 256K

Weights

Open weights

vs Open weights