ModelCap

Current AI model comparison

Exact identities · public evidence

Anthropic

Claude Opus 5

Position

#4

Index

86.2

Measured

6 public benchmark observations across 6 boards

Comparison side 1

Meituan

LongCat 2.0

Position

#11

Index

79.0

Estimated

global-corpus-prior over 183 held-out anchors (7%); launch card against 4 resolved peers on 6 rows (93%); no cross-lab optimism probe available; shrunk 1.9 toward the measured corpus

Comparison side 2

Output / 1M

$25.00

vs $1.20

Context

1M

vs 1M

Weights

API only

vs Open weights