Skip to content

forecastingresearch/forecastbench

View on GitHub ↗Related repositories →

A dynamic forecasting benchmark for LLMs

active 2024-09-302026-08-25 (UTC)

Complete coverage26,656 / 26,656 hourly files (100%) · 2 absent upstream2023-08-152026-08-29 (UTC)
Events
361
Pushes
132
Pull requests
6
Issues
50
Stars
31
Forks
5

Activity over time

Daily event counts in the loaded window

Line chart, 695 days from 2024-09-30 to 2026-08-25. Pushes: 132 total, peak 5 in a day. Pull requests: 6 total, peak 4 in a day. Issues: 50 total, peak 4 in a day. Comments: 21 total, peak 2 in a day. Stars: 31 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
houtanb198130314
zjac0bs5230
nikbpetrov5002
trashhalo2001
jcanedy1001
jmacd8671001
connachermurphy1000
NielsRogge1001
coderabbitai[bot]1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#256jmacd8672026-07-23 15:01
    add logo for Vaticinus
  • Issue comment#233coderabbitai[bot]2026-07-09 19:42
    fix: polymarket deprecated endpoint update
  • Issue#8houtanb2026-05-29 13:21
    Data: Kalshi
  • Issue comment#179nikbpetrov2026-05-16 10:10
    fix: rename `forecast_due_date` in `resolve()` signature and update related tests
  • Issue#191houtanb2026-05-15 21:34
    website: fix spurious hover effect in explore graph legend
  • Issue#191houtanb2026-05-15 21:34
    website: fix spurious hover effect in explore graph legend
  • Issue#185houtanb2026-04-30 09:27
    Generate analysis dataset
  • Issue#183houtanb2026-04-30 09:04
    Quantile questions
  • Issue#172houtanb2026-04-17 12:12
    Reintroduce combo questions
  • Issue#8houtanb2026-04-17 12:08
    Data: Kalshi
  • Issue#135houtanb2026-03-29 16:33
    Handle edge cases (very few) where questions are marked as resloved but resolved_to is non 0/1
  • Issue comment#160houtanb2026-02-23 10:57
    add local dev config for website
  • Issue comment#160houtanb2026-02-23 07:24
    add local dev config for website
  • Pull request#158houtanb2026-02-13 17:45
  • Issue#155houtanb2025-11-18 22:04
    revert acled bug fix
  • Issue#154houtanb2025-10-29 10:34
    Add comments of people who like FB, logos of submitting orgs
  • Issue#153trashhalo2025-10-16 13:55
    release historic difficulty adjustments for reproducibility
  • Issue comment#153trashhalo2025-10-16 13:55
    release historic difficulty adjustments for reproducibility
  • Issue#103houtanb2025-10-08 10:31
    ACLED question bugs
  • Issue comment#107houtanb2025-10-08 10:26
    Fix Metaculus question bank bug
  • Issue#108houtanb2025-10-08 10:25
    Market questions check
  • Issue comment#144houtanb2025-10-08 08:24
    Release nightly resolution updates before 100d cutoff
  • Issue#144houtanb2025-10-08 08:24
    Release nightly resolution updates before 100d cutoff
  • Issue#139houtanb2025-10-06 18:54
    rescale difficulty-adjusted Brier scores
  • Issue#140houtanb2025-10-06 18:54
    x% equivalent forecaster

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 31 stars here means stars gained during the window, not the repo's star count.