Model Comparison

GPT 6.2 Astra vs Qwen3.5 4b

GPT 6.2 Astra ranks #3 on the AI IQ leaderboard with an estimated IQ of 142, 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
GPT 6.2 AstraOpenAIQwen3.5 4bAlibaba
Rank#3#172
IQ14290
Abstract Reasoning13477
Mathematical Reasoning153104
Academic Reasoning134103
Programmatic Reasoning15088
Computer Use15175
Reliability137101
Knowledge Work13279
Emotional Reasoning——
Effective Cost / 1M Tokens$28.15$0.10
Sticker Price / 1M I/O Tokens$48.00$0.18
Speed—17 tok/s
Context Window1.1M262K
Released2026-11-172026-03-02
Open WeightsNoYes