ModelCap

Current AI model comparison

Exact identities · public evidence

Anthropic

Claude Haiku 4.5

Position

#64

Index

55.3

Measured

3 public benchmark observations across 3 boards

Comparison side 1

DeepSeek

DeepSeek V3.1 Terminus

Position

#66

Index

54.1

Measured

3 public benchmark observations across 3 boards

Comparison side 2

Output / 1M

$5.00

vs $1.00

Context

200K

vs 164K

Weights

API only

vs Open weights