ModelCap

Current AI model comparison

Exact identities · public evidence

IFM

K2 Horizon 32B

Position

#90

Index

48.4

Estimated

global-corpus-prior over 188 held-out anchors (51%); launch card against 2 resolved peers on 8 rows (49%); exceeds every named peer on 1 of 8 rows; optimism haircut 1.3 from cross-lab-probe; shrunk 4.7 up toward the measured corpus

Comparison side 1

Qwen

Qwen3 Coder 30B A3B Instruct

Position

#93

Index

48.0

Estimated

publisher-corpus-prior over 188 held-out anchors (7%); launch card against 3 resolved peers on 4 rows (93%); no cross-lab optimism probe available; shrunk 0.2 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs $0.28

Context

vs 262K

Weights

Open weights

vs Open weights