ModelCap

Current AI model comparison

Exact identities · public evidence

MiniMaxAI

MiniMax M1 80k

Position

#77

Index

51.2

Estimated

global-corpus-prior over 185 held-out anchors (19%); launch card against 5 resolved peers on 9 rows (81%); exceeds every named peer on 1 of 9 rows; optimism haircut 0 from cross-lab-probe; shrunk 0.5 up toward the measured corpus

Comparison side 1

Qwen

Qwen3 235B A22B

Position

#80

Index

50.3

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

Unavailable

vs $1.82

Context

1M

vs 131K

Weights

Open weights

vs Open weights