Model Comparison

Granite 4.2 30b vs Minimax M3

Granite 4.2 30b ranks #118 on the AI IQ leaderboard with an estimated IQ of 98, while Minimax M3 ranks #45 on the AI IQ leaderboard with an estimated IQ of 117. The table below puts the two models side by side across the six reasoning dimensions, emotional reasoning, cost, speed, and context window.

Where They Sit on the IQ Bell Curve
Both models highlighted on the standard normal IQ distribution of every tracked model
IQ Dimensions Head to Head
The six scored Composite IQ dimensions, side by side
Domains Head to Head
Applied domain composite scores where at least one model is measured
Granite 4.2 30bUS (Other)Minimax M3MiniMax
Rank#118#45
IQ98117
Abstract Reasoning9190
Mathematical Reasoning96123
Academic Reasoning107126
Programmatic Reasoning92120
Computer Use99117
Reliability104124
Emotional Reasoning—104
Effective Cost / 1M Tokens$0.58$3.44
Sticker Price / 1M I/O Tokens$0.81$1.50
Speed77 tok/s98 tok/s
Context Window524K1M
Released2026-08-252026-06-01
Open WeightsYesYes