Model Comparison

Deepseek V3.2 vs Grok 4.3

Deepseek V3.2 ranks #128 on the AI IQ leaderboard with an estimated IQ of 101, while Grok 4.3 ranks #83 on the AI IQ leaderboard with an estimated IQ of 111. The table below puts the two models side by side across the seven capability 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 seven scored Composite IQ dimensions, side by side
Domains Head to Head
Applied domain composite scores where at least one model is measured
Deepseek V3.2DeepSeekGrok 4.3xAI
Rank#128#83
IQ101111
Abstract Reasoning7993
Mathematical Reasoning102118
Academic Reasoning118126
Programmatic Reasoning111105
Computer Use100110
Reliability101119
Knowledge Work96110
Emotional Reasoning—93
Effective Cost / 1M Tokens$1.84$1.69
Sticker Price / 1M I/O Tokens$0.70$3.75
Speed33 tok/s96 tok/s
Context Window—1M
Released2025-12-012026-04-17
Open WeightsYesNo