ModelCap

Current AI model comparison

Exact identities · public evidence

Meta

Llama 3.3 70B Instruct

Position

#175

Index

20.6

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Thinking Machines

Inkling Small

Position

#31

Index

58.9

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

$0.32

vs $1.20

Context

131K

vs 524K

Weights

Gated access

vs Open weights