ModelCap
Current AI model comparison
Exact identities · public evidence
Ornith Ai
Ornith 1.5 35B A3B
Position
#36
Index
66.2
Estimated
global-corpus-prior over 185 held-out anchors (22%); launch card against 2 resolved peers on 10 rows (78%); exceeds every named peer on 10 of 10 rows; optimism haircut 0 from cross-lab-probe; shrunk 3.6 toward the measured corpus
Comparison side 1
Qwen
Qwen3.8 27B
Position
#39
Index
65.5
Measured
4 public benchmark observations across 4 boards
Comparison side 2
Output / 1M
Unavailable
vs $3.00
Context
—
vs 1M
Weights
Open weights
vs Open weights