Model Comparison

Granite 4.2 3b vs Qwen3.5 4b

Granite 4.2 3b ranks #175 on the AI IQ leaderboard with an estimated IQ of 87, while Qwen3.5 4b ranks #172 on the AI IQ leaderboard with an estimated IQ of 90. 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
Granite 4.2 3bUS (Other)Qwen3.5 4bAlibaba
Rank#175#172
IQ8790
Abstract Reasoning8277
Mathematical Reasoning78104
Academic Reasoning97103
Programmatic Reasoning9988
Computer Use7075
Reliability94101
Knowledge Work9279
Emotional Reasoning——
Effective Cost / 1M Tokens$0.07$0.10
Sticker Price / 1M I/O Tokens$0.15$0.18
Speed40 tok/s17 tok/s
Context Window131K262K
Released2026-08-252026-03-02
Open WeightsYesYes