ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3 Omni 30B A3B Instruct
Position
#100
Index
54.3
Estimated
publisher-corpus-prior over 215 held-out anchors (10%); launch card against 4 resolved peers on 4 rows (90%); exceeds every named peer on 1 of 4 rows; no cross-lab optimism probe available; shrunk 0.2 up toward the measured corpus
Comparison side 1
Z.ai
GLM 5 Turbo
Position
#97
Index
54.8
Measured
publisher-corpus-prior over 215 held-out anchors (63%); 1 specialist-board observation at 1.2% support (37%); shrunk 24.9 up toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs $4.00
Context
—
vs 203K
Weights
Restricted license
vs API only