ModelCap
Current AI model comparison
Exact identities · public evidence
MiniMax
MiniMax M3.1 Flash
Position
#28
Index
75.7
Measured
publisher-corpus-prior over 210 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 1.6 toward the measured corpus
Comparison side 1
OpenAI
GPT-6.1 Terra
Position
#29
Index
75.4
Measured
1 reported rows against measured corpus ladders (21%); publisher-corpus-prior over 210 held-out anchors (14%); opens above measured predecessor openai/gpt-5.6-terra on same-family ordering evidence (53%); 1 specialist-board observation at 2.5% support (12%); shrunk 3.5 toward the measured corpus
Comparison side 2
Output / 1M
$0.30
vs $5.00
Context
1M
vs 1M
Weights
Restricted license
vs No linked weights