ModelCap

Current AI model comparison

Exact identities · public evidence

Qwen

Qwen3 Coder Next

Position

#116

Index

54.0

Measured

1 public benchmark observation across 1 board

Comparison side 1

Qwen

Qwen3 VL 30B A3B Instruct

Position

#165

Index

42.4

Estimated

4 reported rows against measured corpus ladders (50%); publisher-corpus-prior over 232 held-out anchors (50%); shrunk 11.3 up toward the measured corpus

Comparison side 2

Output / 1M

$0.80

vs $0.60

Context

262K

vs 262K

Weights

Open weights

vs Open weights