ModelCap

Current AI model comparison

Exact identities · public evidence

OpenAI

GPT-5.4 Nano

Position

#80

Index

50.8

Measured

4 public benchmark observations across 4 boards

Comparison side 1

Qwen

Qwen3 Coder 30B A3B Instruct

Position

#91

Index

48.4

Estimated

publisher-corpus-prior over 194 held-out anchors (7%); launch card against 3 resolved peers on 4 rows (93%); no cross-lab optimism probe available; shrunk 0.1 up toward the measured corpus

Comparison side 2

Output / 1M

$1.25

vs $0.28

Context

400K

vs 262K

Weights

API only

vs Open weights