ModelCap

Current AI model comparison

Exact identities · public evidence

Poolside

Laguna XS 2.1

Position

#64

Index

54.4

Estimated

3 reported rows against measured corpus ladders (31%); global-corpus-prior over 183 held-out anchors (69%); shrunk 1.9 toward the measured corpus

Comparison side 1

Thinking Machines

Inkling Small

Position

#67

Index

53.2

Measured

5 public benchmark observations across 5 boards

Comparison side 2

Output / 1M

$0.12

vs $1.20

Context

262K

vs 1M

Weights

Restricted license

vs Open weights