ModelCap

Current AI model comparison

Exact identities · public evidence

Arcee AI

Arcee SuperNova v1

Position

#199

Index

22.0

Inherited

finetune of meta-llama/llama-3.1-70b-instruct · finetune (100%)

Comparison side 1

Qwen

Qwen2.5 Omni 7B

Position

#196

Index

22.8

Estimated

publisher-corpus-prior over 209 held-out anchors (24%); launch card against 2 resolved peers on 5 rows (77%); exceeds every named peer on 2 of 5 rows; optimism haircut 2.4 from cross-lab-probe; shrunk 10.1 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Restricted license

vs Restricted license