ModelCap

Current AI model comparison

Exact identities · public evidence

Meta

Llama 4 Maverick

Position

#94

Index

25.1

Measured

4 public benchmark observations across 4 boards

Comparison side 1

Qwen

Qwen3 4B Instruct 2507

Position

#105

Index

23.5

Estimated

start rank interpolated from the launch card's own comparison table against resolved catalogue peers, discounted for measured cross-lab optimism

Comparison side 2

Output / 1M

$0.80

vs Unavailable

Context

1M

vs 262K

Weights

Gated access

vs Open weights