ModelCap

Current AI model comparison

Exact identities · public evidence

CohereLabs

command a reasoning 08 2025

Position

#124

Index

33.0

Inherited

finetune of cohere/command-a · finetune (100%)

Comparison side 1

OpenAI

GPT-4o-mini

Position

#120

Index

34.5

Measured

publisher-corpus-prior over 183 held-out anchors (59%); 1 specialist-board observation at 2.1% support (41%); shrunk 21.6 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs $0.60

Context

—

vs 128K

Weights

Gated access

vs API only