Explore - ForecastBench
forecastbench.org · 211 words · saved by 1 readers
A dynamic, continuously-updated forecasting benchmark.
State-of-the-art model forecasting performance over time This interactive visualization charts the evolution of AI forecasting accuracy on ForecastBench. Each point represents a model's Brier Index across all questions it predicted on (higher is better), plotted by model release date. Orange points mark models that were state of the art (SOTA) when released; they had the best benchmark performance given their release date. Vertical bars indicate 95% confidence intervals. Gray points show non-SOTA models. The orange dashed line shows the estimated linear trend for SOTA performance…
saved by
related reading
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- LLMs Are Closing the Gap on Human Superforecasterssubstack.com
- The AI Superforecasters Are Here - by Scott Alexanderastralcodexten.com
- The Unreasonable Difficulty of Time Series Forecastingsuzyahyah.github.io
- Pitfalls in Evaluating Language Model Forecastersarxiv.org
- Training LLMs to Predict World Events (Guest Post with Mantic) - Thinking Machines Labthinkingmachines.ai
- CAIS AI Dashboarddashboard.safe.ai
- A statistical approach to model evaluations \ Anthropicanthropic.com
- AI Futures Model: Dec 2025 Updateblog.ai-futures.org
- How well did forecasters predict 2025 AI progress? | Epoch AIepoch.ai
- How fast is AI improving? - AI Digesttheaidigest.org
- AI Futures Model: Dec 2025 Updateblog.aifutures.org