ModelCap
Current AI model comparison
Exact identities · public evidence
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 1
OpenAI
GPT-5.6 Terra
Position
#18
Index
76.1
Measured
6 public benchmark observations across 6 boards
Comparison side 2
Output / 1M
$1.20
vs $12.00
Context
1M
vs 1M
Weights
Open weights
vs API only