ModelCap

Current AI model comparison

Exact identities · public evidence

Meta

Llama 4 Scout

Position

#105

Index

22.4

Measured

4 public benchmark observations across 4 boards

Comparison side 1

Microsoft

HARC Qwen2.5 7B Instruct

Position

#103

Index

22.5

Inherited

merge · merge

Comparison side 2

Output / 1M

$0.30

vs Unavailable

Context

1.3M

vs

Weights

Gated access

vs Open weights