Skip to content

Every Eval Ever is a shared schema and crowdsourced eval database. It defines a standardized metadata format for storing AI evaluation results — from leaderboard scrapes and research papers to local evaluation runs — so that results from different frameworks can be compared, reproduced, and reused.

active 2025-10-202026-08-10 (UTC)

Partial coverage10,768 / 10,984 hourly files (98%) · 2 absent upstream · 214 failed, retryable2025-05-102026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
373
Pushes
113
Pull requests
42
Issues
9
Stars
16
Forks
5

Activity over time

Daily event counts in the loaded window

Line chart, 295 days from 2025-10-20 to 2026-08-10. Pushes: 113 total, peak 12 in a day. Pull requests: 42 total, peak 3 in a day. Issues: 9 total, peak 1 in a day. Comments: 75 total, peak 10 in a day. Stars: 16 total, peak 4 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
damian19967238138
nelaturuharsha583844
Copilot270019
akornilo20845
tommasocerruti16516
mrshu150111
evijit14514
janbatzner10531
yifanmai6420
sanchit-ahuja6320
Erotemic6121
borgr6302
andrewtran1176112
yananlong5005
Asaf-Yehudai3030
baberabb2020
github-actions[bot]2200
joeda2010
snakefood32321001
elronbandel1010

Recent activity

Latest issues, pull requests and releases

  • Issue comment#188borgr2026-08-08 04:11
    Convert BountyBench run logs through an adapter, with per-configuration record identity
  • Issue comment#230mrshu2026-08-07 16:34
    Warn when two names for one publisher split its datastore directory
  • Pull request#199tommasocerruti2026-07-04 22:10
  • Issue#165nelaturuharsha2026-06-09 06:18
    [adapter] Update cocoabench adapter
  • Issue#159borgr2026-06-04 22:15
    Automatically add new information - CI with adapters
  • Issue#88nelaturuharsha2026-05-13 19:30
    [Feature] Expand test-suite and add automatic trigger for running it on PRs
  • Pull request#135Erotemic2026-05-13 19:30
  • Pull request#132Erotemic2026-05-08 01:53
  • Issue comment#124tommasocerruti2026-04-28 18:04
    feat: add Vals.ai adapter
  • Issue comment#119snakefood32322026-04-24 21:49
    Inconsistency in evaluator_relationship
  • Pull request#108yifanmai2026-04-23 07:31
  • Issue comment#100damian19962026-04-07 16:57
    fix: correct save_to_file creating directory at file path
  • Pull request#102mrshu2026-04-06 17:32
  • Pull request#89damian19962026-03-25 11:16
  • Pull request#81elronbandel2026-03-23 22:05
  • Issue#86nelaturuharsha2026-03-20 19:10
    Update the github action to also upload to pypi
  • Issue#59nelaturuharsha2026-03-19 21:43
    Handling Inspect outputs that are not in samples
  • Pull request#74nelaturuharsha2026-03-18 19:25
  • Pull request#71j-chim2026-03-17 21:53
  • Issue comment#63StevenDillmann2026-03-13 03:15
    [Submission] Add Terminal-Bench 2.0 adapter script
  • Issue#58damian19962026-03-11 00:51
    Conversion from inspect bfcl benchmark fail
  • Issue#60damian19962026-03-09 03:02
    arc_easy and arc_challenge overwrite each other on conversion with the Inspect AI converter
  • Issue#59joeda2026-03-06 11:13
    Handling Inspect outputs that are not in samples
  • Issue comment#52yananlong2026-03-06 04:15
    Add metric identity and deterministic aggregate-instance linkage fields
  • Issue comment#52dmjoy2026-03-05 17:43
    Add metric identity and deterministic aggregate-instance linkage fields

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 16 stars here means stars gained during the window, not the repo's star count.