FYI, ForecastBench [1] tests LLMs' out-of-sample forecasting accuracy.

The ForecastBench Tournament Leaderboard [2] allows external participants to submit models, most of whom provide some sort of web search / news scaffolding to improve model forecasting accuracy.

[1] https://www.forecastbench.org/

[2] https://www.forecastbench.org/tournament/