Compare what each model's ECI rests on

Each row is a benchmark, with both models' scores on it, placed at the ECI each score implies under Epoch's model, so that every benchmark is on the same ECI scale. Hardest benchmarks (highest ECI at a 50% score) at the top.

Hover over or tap a dot for the score behind it; click a benchmark name for Epoch's page on it.

† Epoch rescales this benchmark's scores before fitting: random guessing counts as 0% and, for some, a maximum below 100% counts as 100%. Scores here are the rescaled ones; hover a dot for the raw score. Data: Epoch AI Benchmarking Hub, ECI as published (data as of Nov 10, 2026).