Bench to the Future 2 — Calibration Error
Forecasting · 2026-04-20
The calibration component of the BTF-2 Brier decomposition measures the squared gap between stated forecast probabilities and observed outcome frequencies. Lower calibration error is better.
Top models (lower is better)
| Model | Score |
|---|---|
| Grok 4.20 | 0.0 |
| Opus 4.6 | 0.0 |
| GPT-5.4 | 0.0 |
| Gemini 3.1 Pro Preview | 0.0 |