Artificial intelligence · 2024
Test-time compute scaling
Accuracy rises smoothly with how long the model is allowed to think.
o1's results showed performance scaling with inference compute as well as training compute. Longer reasoning, parallel sampling and search turned extra compute at answer time into reliable gains, reshaping hardware demand toward inference.
What it built on 2
What it led to 3
Related measurements
The dashed line marks when it first worked.
Best AI score on GPQA Diamond Latest: 95.8 % correct (2026) Source: Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv); Anthropic: Claude 3 public launch (March 4, 2024)
Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)