Personal AI Benchmarking

44 AI capability milestones I track personally, with current capability scores and my own forecasts compared against GPT O3's predictions. Click any item name to see its description.

Benchmark Item Current Capability GPT O3 Forecast CG Forecast Delta
High (8-10)
Medium (5-7)
Low (1-4)
GPT O3 Forecast
CG Forecast

Data sourced from personal tracking. Forecasts are speculative and updated periodically. Last updated: February 2026.