ModelCap
Current AI model comparison
Exact identities · public evidence
MiniMax
MiniMax M2-her
Position
#89
Index
28.9
Estimated
publisher corpus prior · leave-one-anchor-out calibrated
Comparison side 1
Qwen
Qwen3 30B A3B
Position
#111
Index
24.0
Measured
2 public benchmark observations across 2 boards
Comparison side 2
Output / 1M
$1.20
vs $0.50
Context
66K
vs 131K
Weights
API only
vs Open weights