Model Comparison

Deepseek V4 Pro vs Sonnet 5

Deepseek V4 Pro ranks #31 on the AI IQ leaderboard with an estimated IQ of 123, while Sonnet 5 ranks #27 on the AI IQ leaderboard with an estimated IQ of 125. 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 V4 ProDeepSeekSonnet 5Anthropic
Rank#31#27
IQ123125
Abstract Reasoning109105
Mathematical Reasoning132131
Academic Reasoning130129
Programmatic Reasoning129131
Computer Use123129
Reliability118123
Knowledge Work124124
Emotional Reasoning118117
Effective Cost / 1M Tokens$7.01$38.51
Sticker Price / 1M I/O Tokens$5.28$12.00
Speed110 tok/s82 tok/s
Context Window1M1M
Released2026-04-242026-06-30
Open WeightsYesNo