Skip to content

GoogleCloudPlatform/evalbench

View on GitHub ↗Related repositories →

EvalBench is a flexible framework designed to measure the quality of generative AI (GenAI) workflows around database specific tasks.

active 2025-03-242026-08-13 (UTC)

Partial coverage21,356 / 26,307 hourly files (81%) · 2 absent upstream · 4,951 failed, retryable2023-08-152026-08-15 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.2K
Pushes
590
Pull requests
163
Issues
1
Stars
20
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 508 days from 2025-03-24 to 2026-08-13. Pushes: 590 total, peak 16 in a day. Pull requests: 163 total, peak 8 in a day. Issues: 1 total, peak 1 in a day. Comments: 143 total, peak 11 in a day. Stars: 20 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

Recent activity

Latest issues, pull requests and releases

  • Pull request#521release-please[bot]2026-07-23 18:14
  • Pull request#496dependabot[bot]2026-07-15 14:28
  • Issue comment#473IsmailMehdi2026-07-01 21:50
    Make plugin installation synchronous to avoid timing issues during eval
  • Issue comment#471graceqi-g2026-06-29 23:22
    Move teardown script into finally block
  • Pull request#457minzznguyen2026-06-23 23:52
  • Issue comment#450IsmailMehdi2026-06-19 17:45
    test(bigtable): allow instance/project override via env vars
  • Issue comment#428graceqi-g2026-06-16 23:37
    Package DEA scenarios in one request for sequential execution
  • Pull request#413release-please[bot]2026-06-11 16:15
  • Issue comment#415omkargaikwad232026-06-06 17:34
    refactor: introduce AgentCliGenerator base to unify CLI generator handling
  • Issue comment#408omkargaikwad232026-06-03 11:39
    feat: add AgyCliGenerator support to evaluator and models, including test suite and configuration datasets
  • Issue comment#404graceqi-g2026-06-01 22:08
    Set up generator class and auth for Data Engineering Agent
  • Pull request#406erinlimbogoogle2026-05-28 00:53
  • Pull request#405helloeve2026-05-27 01:55
  • Pull request#405helloeve2026-05-27 01:55
  • Pull request#393dependabot[bot]2026-05-13 19:01
  • Pull request#393dependabot[bot]2026-05-13 19:01
  • Pull request#382dependabot[bot]2026-05-09 07:17
  • Pull request#377IsmailMehdi2026-05-08 03:09
  • Pull request#375dependabot[bot]2026-05-07 19:40
  • Pull request#375dependabot[bot]2026-05-07 19:40
  • Issue comment#365IsmailMehdi2026-05-03 19:26
    Verifier branch
  • Issue comment#367saurabh-net2026-05-03 06:30
    feat: Add dbt Scorers for Agent Evaluations
  • Issue comment#366saurabh-net2026-05-03 05:39
    feat: Add GCS Artifacts Reporter for Agent Evaluations
  • Pull request#365IsmailMehdi2026-05-02 23:39
  • Issue comment#363IsmailMehdi2026-05-01 00:59
    Verifier branch

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 20 stars here means stars gained during the window, not the repo's star count.