ModelCap

Current AI model comparison

Exact identities · public evidence

MiniMax

MiniMax M3.1 Flash

Position

#33

Index

74.1

Measured

publisher-corpus-prior over 214 held-out anchors (6%); 1 specialist-board observation at 2.5% support (5%); launch card against 5 resolved peers on 6 rows (89%); optimism haircut 0 from cross-lab-probe; shrunk 1.7 toward the measured corpus

Comparison side 1

OpenAI

GPT-6.2 Astra

Position

#22

Index

77.9

Measured

1 reported rows against measured corpus ladders (20%); publisher-corpus-prior over 214 held-out anchors (13%); opens above measured predecessor openai/gpt-6-astra on same-family ordering evidence (47%); 3 specialist-board observations at 4.9% support (21%); shrunk 3.8 toward the measured corpus

Comparison side 2

Output / 1M

$0.60

vs $40.00

Context

1M

vs 1M

Weights

Restricted license

vs No linked weights