Skip to content

A benchmark that challenges language models to code solutions for scientific problems

active 2024-07-152026-06-29 (UTC)

Partial coverage15,174 / 18,597 hourly files (82%) · 2 absent upstream · 3,422 failed, retryable2024-06-272026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
184
Pushes
50
Pull requests
16
Issues
14
Stars
77
Forks
16

Activity over time

Daily event counts in the loaded window

Line chart, 715 days from 2024-07-15 to 2026-06-29. Pushes: 50 total, peak 7 in a day. Pull requests: 16 total, peak 4 in a day. Issues: 14 total, peak 3 in a day. Comments: 6 total, peak 1 in a day. Stars: 77 total, peak 8 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
pre-commit-ci[bot]222200
Zilinghan16771
mtian813922
YanxinLu10640
klieret5500
ZeYang10255011
ofirpress3001
zrait1000
rong-xyz1010
tomtyiu1000
HariSeldon01010
Belzedar941000
DavidBellamy1001
Kreijstal1000
idavidrein1000
John-Boccio1000
XuGW-Kevin1000
HelloWorldLTY1000

Recent activity

Latest issues, pull requests and releases

  • Pull request#52ZeYang10252025-10-07 01:22
  • Issue comment#51ZeYang10252025-10-06 23:28
    Is the loading setting same as HumanEval
  • Issue#51ZeYang10252025-10-06 23:28
    Is the loading setting same as HumanEval
  • Issue#51HelloWorldLTY2025-10-06 00:53
    Is the loading setting same as HumanEval
  • Issue#50tomtyiu2025-10-04 17:51
    benchmark EpistemeAI's gpt-oss-20b
  • Pull request#45rong-xyz2025-07-10 10:37
  • Issue#40ZeYang10252025-06-30 18:49
    error
  • Issue#44ZeYang10252025-06-30 18:49
    The tests always fail
  • Issue#43John-Boccio2025-05-02 00:44
    Some example's `ground_truth_code` do not pass the tests in dev set
  • Issue#18ofirpress2025-02-02 12:20
    add new claude-3-5-sonnet-20241022
  • Issue#21ofirpress2025-02-02 12:20
    Add o1 17/12 To the Leaderboard
  • Issue comment#25Zilinghan2025-02-02 03:05
    Deepseek R1 Evaluation Results?
  • Issue#25Zilinghan2025-02-02 03:05
    Deepseek R1 Evaluation Results?
  • Pull request#28Zilinghan2025-02-02 03:05
  • Pull request#28Zilinghan2025-02-02 03:04
  • Pull request#27Zilinghan2025-02-02 03:01
  • Pull request#27Zilinghan2025-02-02 03:00
  • Issue comment#20ofirpress2025-01-25 08:41
    Ground Truth Code for problems_all.jsonl
  • Pull request#15Zilinghan2025-01-25 05:37
  • Pull request#22Zilinghan2025-01-25 05:27
  • Pull request#22Zilinghan2025-01-24 22:23
  • Issue comment#21DavidBellamy2024-12-23 05:25
    Add o1 17/12 To the Leaderboard
  • Pull request#19YanxinLu2024-11-04 05:26
  • Pull request#19YanxinLu2024-11-04 05:25
  • Issue#18Kreijstal2024-10-30 06:24
    add new claude-3-5-sonnet-20241022

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 77 stars here means stars gained during the window, not the repo's star count.