ModelCap

Current AI model comparison

Exact identities · public evidence

Meta

Llama 3.1 8B Instruct

Position

#207

Index

3.1

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Mistral AI

Mixtral 8x22B Instruct

Position

#205

Index

4.8

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

$0.08

vs $6.00

Context

131K

vs 66K

Weights

Gated access

vs Open weights