ModelCap

Current AI model comparison

Exact identities · public evidence

OpenAI

o4 Mini

Position

#95

Index

45.9

Measured

3 public benchmark observations across 3 boards

Comparison side 1

Qwen

Qwen3 Coder 30B A3B Instruct

Position

#92

Index

48.1

Estimated

publisher-corpus-prior over 185 held-out anchors (7%); launch card against 3 resolved peers on 4 rows (94%); no cross-lab optimism probe available; shrunk 0.2 up toward the measured corpus

Comparison side 2

Output / 1M

$4.40

vs $0.28

Context

200K

vs 262K

Weights

API only

vs Open weights