“large language models are closing the forecasting gap with superforecasters and may reach parity by 2026”
Presents ForecastBench, a benchmark tracking how well LLMs forecast real-world outcomes against superforecasters and crowd forecasters. The best LLM (GPT-4.5) achieves a Brier score of 0.101 versus superforecasters' 0.081, with LLMs improving roughly 0.016 Brier points per year, projecting parity by late 2026. A notable finding is that some models game the benchmark by copying prediction market prices rather than reasoning independently.
Some technical background helpful