Model Comparison

Deepseek V4 Pro vs Fable 5

Deepseek V4 Pro ranks #33 on the AI IQ leaderboard with an estimated IQ of 117, while Fable 5 ranks #1 on the AI IQ leaderboard with an estimated IQ of 137. 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
Deepseek V4 ProDeepSeekFable 5Anthropic
Rank#33#1
IQ117137
Abstract Reasoning105129
Mathematical Reasoning113143
Academic Reasoning135145
Programmatic Reasoning117144
Computer Use120139
Reliability109120
Emotional Reasoning118125
Effective Cost / 1M Tokens$2.66$76.55
Sticker Price / 1M I/O Tokens$1.30$60.00
Speed71 tok/s71 tok/s
Context Window1M1M
Released2026-04-242026-06-09
Open WeightsYesNo