ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3 Coder Next
Position
#99
Index
51.3
Measured
1 public benchmark observation across 1 board
Comparison side 1
StepFun
Step 3.7 Flash
Position
#96
Index
51.8
Estimated
3 reported rows against measured corpus ladders (19%); global-corpus-prior over 203 held-out anchors (18%); measured predecessor stepfun/step-3.5-flash less the succession penalty (63%); shrunk 0.7 up toward the measured corpus
Comparison side 2
Output / 1M
$0.80
vs $1.15
Context
262K
vs 262K
Weights
Open weights
vs Open weights