ModelCap
Current AI model comparison
Exact identities · public evidence
Amazon
Nova 2 Lite
Position
#98
Index
26.6
Measured
2 public benchmark observations across 2 boards
Comparison side 1
Qwen
Qwen2.5 Coder 3B Instruct
Position
#103
Index
24.4
Estimated
publisher corpus prior · leave-one-anchor-out calibrated
Comparison side 2
Output / 1M
$2.50
vs Unavailable
Context
1M
vs 33K
Weights
API only
vs Restricted license