Issues

• Full run on question-set-v2

  Feature

  forecastingresearch/forecastbench-sim#26 · Filter by author fdrocha opened on Oct 27, 2026
  

• Prepare question-set-v2

  forecastingresearch/forecastbench-sim#25 · Filter by author fdrocha opened on Oct 27, 2026
  

• FreeCiv new questions

  forecastingresearch/forecastbench-sim#24 · Filter by author fdrocha opened on Oct 27, 2026
  

• Starsim new questions

  forecastingresearch/forecastbench-sim#23 · Filter by author fdrocha opened on Oct 27, 2026
  

• Micropolis new questions

  forecastingresearch/forecastbench-sim#22 · Filter by author fdrocha opened on Oct 27, 2026
  

• New question-set generation: decide on selection approach

  forecastingresearch/forecastbench-sim#21 · Filter by author fdrocha opened on Oct 27, 2026
  

• (Optional) First leaderboard with new models

  forecastingresearch/forecastbench-sim#20 · Filter by author fdrocha opened on Oct 27, 2026
  

• Decide whether to run variants with tool use/web search

  forecastingresearch/forecastbench-sim#19 · Filter by author fdrocha opened on Oct 27, 2026
  

• Pilot: validate the prepared question set, prompting and scoring against the paper

  forecastingresearch/forecastbench-sim#18 · Filter by author fdrocha opened on Oct 27, 2026
  

• Unified scoring code producing leaderboard.json

  forecastingresearch/forecastbench-sim#17 · Filter by author fdrocha opened on Oct 27, 2026
  

• Unified prompting code on fri-utils

  forecastingresearch/forecastbench-sim#16 · Filter by author fdrocha opened on Oct 27, 2026
  

• Prepared question set v1 from the paper's questions and runs

  forecastingresearch/forecastbench-sim#15 · Filter by author fdrocha opened on Oct 27, 2026
  

• Three FreeCiv fork scripts still roll fresh dice by default

  forecastingresearch/forecastbench-sim#13 · Filter by author elsehow opened on Oct 15, 2026