ModelCap
Current AI model comparison
Exact identities · public evidence
Meta
Muse Spark Open
Position
#15
Index
79.6
Estimated
publisher-corpus-prior over 213 held-out anchors (22%); launch card against 5 resolved peers on 11 rows (78%); exceeds every named peer on 3 of 11 rows; optimism haircut 0 from cross-lab-probe; shrunk 1 up toward the measured corpus
Comparison side 1
Xiaomi
MiMo-V2.6-Pro
Position
#18
Index
78.8
Measured
3 public benchmark observations across 3 boards
Comparison side 2
Output / 1M
$4.25
vs $0.87
Context
1M
vs 1M
Weights
Gated access
vs Open weights