ModelCap

Current AI model comparison

Exact identities · public evidence

Allen Institute

Olmo Hybrid 7B

Position

#208

Index

13.7

Estimated

publisher-corpus-prior over 203 held-out anchors (11%); launch card against 2 resolved peers on 6 rows (89%); exceeds every named peer on 2 of 6 rows; no cross-lab optimism probe available; shrunk 0.8 up toward the measured corpus

Comparison side 1

Microsoft

Phi 4 reasoning plus

Position

#211

Index

12.6

Inherited

finetune of microsoft/phi-4 · finetune (100%)

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Open weights