ModelCap

Current AI model comparison

Exact identities · public evidence

Mistral AI

Mistral Small 4

Position

#97

Index

54.1

Measured

1 public benchmark observation across 1 board

Comparison side 1

StepFun

Step 3.7 Flash

Position

#96

Index

54.2

Estimated

3 reported rows against measured corpus ladders (20%); global-corpus-prior over 209 held-out anchors (17%); measured predecessor stepfun/step-3.5-flash less the succession penalty (63%); shrunk 0.6 up toward the measured corpus

Comparison side 2

Output / 1M

$0.60

vs $1.15

Context

262K

vs 262K

Weights

Open weights

vs Open weights