ModelCap

Current AI model comparison

Exact identities · public evidence

Cohere

North Mini Code

Position

#129

Index

33.6

Estimated

3 reported rows against measured corpus ladders (57%); publisher-corpus-prior over 186 held-out anchors (43%); shrunk 13.7 toward the measured corpus

Comparison side 1

Google

Gemma 3 27B

Position

#117

Index

37.7

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

Free

vs $0.45

Context

256K

vs 131K

Weights

Open weights

vs Gated access