ModelCap
Current AI model comparison
Exact identities · public evidence
Mistral AI
Mistral Small 4
Position
#118
Index
41.1
Measured
1 public benchmark observation across 1 board
Comparison side 1
Qwen
Qwen3.5 4B
Position
#121
Index
39.7
Estimated
publisher-corpus-prior over 197 held-out anchors (28%); launch card against 3 resolved peers on 10 rows (72%); exceeds every named peer on 2 of 10 rows; optimism haircut 0.6 from cross-lab-probe; shrunk 4.3 up toward the measured corpus
Comparison side 2
Output / 1M
$0.60
vs Unavailable
Context
262K
vs —
Weights
Open weights
vs Open weights