ModelCap
Current AI model comparison
Exact identities · public evidence
ByteDance Seed
Seed 2.1 Turbo
Position
#18
Index
76.8
Estimated
global-corpus-prior over 185 held-out anchors (12%); launch card against 2 resolved peers on 3 rows (88%); exceeds every named peer on 1 of 3 rows; no cross-lab optimism probe available; shrunk 3.1 toward the measured corpus
Comparison side 1
DeepSeek
DeepSeek V4 Flash 0731
Position
#26
Index
71.2
Measured
2 public benchmark observations across 2 boards
Comparison side 2
Output / 1M
$2.50
vs $0.18
Context
262K
vs 1.3M
Weights
API only
vs Open weights