ModelCap

Current AI model comparison

Exact identities · public evidence

Poolside

Laguna XS.2

Position

#63

Index

54.9

Estimated

4 reported rows against measured corpus ladders (65%); global-corpus-prior over 183 held-out anchors (35%); shrunk 0.7 toward the measured corpus

Comparison side 1

Qwen

Qwen3 VL 235B A22B Instruct

Position

#59

Index

55.5

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

Unavailable

vs $1.90

Context

—

vs 262K

Weights

Open weights

vs Open weights