ModelCap
Current AI model comparison
Exact identities · public evidence
Anthropic
Claude Sonnet 5.5
Position
#1
Index
91.3
Measured
1 public benchmark observation across 1 board
Comparison side 1
DeepSeek
DeepSeek V4 Pro 0813
Position
#25
Index
73.8
Measured
4 public benchmark observations across 4 boards
Comparison side 2
Output / 1M
$10.00
vs $3.96
Context
1M
vs 1M
Weights
API only
vs Open weights