ModelCap

Current AI model comparison

Exact identities · public evidence

Qwen

Qwen3.8 27B

Position

#68

Index

63.1

Measured

4 public benchmark observations across 4 boards

Comparison side 1

Qwen

Qwen4 Max

Position

#36

Index

72.8

Measured

1 reported rows against measured corpus ladders (22%); publisher-corpus-prior over 214 held-out anchors (14%); opens above measured predecessor qwen/qwen3.8-max on same-family ordering evidence (52%); 1 specialist-board observation at 2.5% support (12%); shrunk 3.8 toward the measured corpus

Comparison side 2

Output / 1M

$2.20

vs $4.27

Context

1M

vs 1M

Weights

Open weights

vs No linked weights