ModelCap

Current AI model comparison

Exact identities · public evidence

OpenAI

GPT-5.1-Codex-Max

Position

#118

Index

23.0

Estimated

publisher corpus prior · leave-one-anchor-out calibrated

Comparison side 1

Qwen

Qwen3 4B Instruct 2507

Position

#115

Index

23.0

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

$10.00

vs Unavailable

Context

400K

vs 262K

Weights

API only

vs Open weights