ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3.5-9B
Position
#102
Index
41.6
Estimated
publisher-corpus-prior over 185 held-out anchors (30%); launch card against 3 resolved peers on 10 rows (71%); exceeds every named peer on 4 of 10 rows; optimism haircut 0.6 from cross-lab-probe; shrunk 3.7 up toward the measured corpus
Comparison side 1
Z.ai
GLM 4.6V
Position
#99
Index
42.7
Measured
2 public benchmark observations across 2 boards
Comparison side 2
Output / 1M
$0.15
vs $0.90
Context
262K
vs 131K
Weights
Open weights
vs Open weights