Skip to content

Benchmark for Repository-Level Code Generation, focus on Executability, Correctness from Test Cases and Usage of Contexts from Cross-file Dependencies

active 2024-06-192026-01-08 (UTC)

Partial coverage16,646 / 21,075 hourly files (79%) · 2 absent upstream · 4,428 failed, retryable2024-03-172026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
73
Pushes
46
Pull requests
4
Issues
1
Stars
17
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 569 days from 2024-06-19 to 2026-01-08. Pushes: 46 total, peak 19 in a day. Pull requests: 4 total, peak 2 in a day. Issues: 1 total, peak 1 in a day. Comments: 4 total, peak 1 in a day. Stars: 17 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
NamCyan494603
wolfmagnate4040
Bruno-Lee1001
Espresso-Kp1000

Recent activity

Latest issues, pull requests and releases

  • Pull request#4wolfmagnate2026-01-08 09:49
  • Pull request#6wolfmagnate2026-01-08 09:47
  • Pull request#6wolfmagnate2025-11-21 09:40
  • Pull request#5wolfmagnate2025-11-21 04:08
  • Issue#3Espresso-Kp2025-08-20 09:30
    execute.py stalls on dependency resolution for test-apps/tornado (hangs at Collecting constantly>=15.1 / attrs>=22.2.0)
  • Issue comment#2NamCyan2025-04-27 16:46
    How to evaluate my own generated code?
  • Issue comment#1NamCyan2025-03-22 13:38
    How to evaluate models like claude / chatgpt?
  • Issue comment#1Bruno-Lee2025-03-20 06:30
    How to evaluate models like claude / chatgpt?
  • Issue comment#1NamCyan2025-02-23 16:14
    How to evaluate models like claude / chatgpt?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 17 stars here means stars gained during the window, not the repo's star count.