ModelCap
Current AI model comparison
Exact identities · public evidence
Kuaishou
KAT-Coder-Pro V2.5
Position
#61
Index
43.3
Estimated
start rank inherited from the measured predecessor in its own product family, less a fixed succession penalty, until independent measurements replace it
Comparison side 1
Qwen
Qwen3 Max Thinking
Position
#64
Index
42.3
Measured
1 public benchmark observation across 1 board
Comparison side 2
Output / 1M
$2.96
vs $3.90
Context
262K
vs 262K
Weights
API only
vs API only