ModelCap

Current AI model comparison

Exact identities · public evidence

Openbmb

MathForm 8B

Position

#104

Index

22.5

Inherited

finetune · finetune

Comparison side 1

Qwen

Qwen3 4B Instruct 2507

Position

#102

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

Unavailable

vs Unavailable

Context

vs 262K

Weights

Open weights

vs Open weights