ModelCap
Current AI model comparison
Exact identities · public evidence
DeepSeek
DeepSeek V4 Flash Vision Exp
Position
#24
Index
71.2
Estimated
publisher-corpus-prior over 183 held-out anchors (12%); launch card against 2 resolved peers on 7 rows (88%); exceeds every named peer on 1 of 7 rows; no cross-lab optimism probe available; shrunk 1.9 toward the measured corpus
Comparison side 1
Qwen
Qwen3.8 Flash
Position
#14
Index
78.0
Measured
1 public benchmark observation across 1 board
Comparison side 2
Output / 1M
$0.66
vs $0.47
Context
1M
vs 1M
Weights
Open weights
vs Restricted license