Skip to content

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)

Python · active 2025-08-112026-06-06 (UTC)

Complete coverage26,537 / 26,537 hourly files (100%) · 2 absent upstream2023-08-152026-08-24 (UTC)
Events
171
Pushes
22
Pull requests
5
Issues
9
Stars
99
Forks
17

Activity over time

Daily event counts in the loaded window

Line chart, 300 days from 2025-08-11 to 2026-06-06. Pushes: 22 total, peak 15 in a day. Pull requests: 5 total, peak 1 in a day. Issues: 9 total, peak 2 in a day. Comments: 14 total, peak 4 in a day. Stars: 99 total, peak 11 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
MXueguang261334
wu-ming23311612
Copilot5004
ArvinZhuang3300
XiaofengWu10283002
shallinan13001
yhshu1000
Zara7hus7ra1001
AbhimanyuAryan1010

Recent activity

Latest issues, pull requests and releases

  • Pull request#23AbhimanyuAryan2026-03-28 10:12
  • Issue comment#16XiaofengWu10282025-12-12 07:26
    Question about the leaderboard and evaluation pipeline.
  • Issue#13MXueguang2025-12-11 20:03
    Tongyi-Deepresearch-30B time cost is expensive
  • Issue comment#16XiaofengWu10282025-12-11 12:24
    Question about the leaderboard and evaluation pipeline.
  • Issue comment#16MXueguang2025-12-11 04:06
    Question about the leaderboard and evaluation pipeline.
  • Issue#16XiaofengWu10282025-12-11 03:21
    Question about the leaderboard and evaluation pipeline.
  • Issue#15yhshu2025-12-09 03:56
    Incomplete response using GPT-oss-120b
  • Issue#14MXueguang2025-12-07 15:07
    Incorrect correct answer in benchmark
  • Issue#14MXueguang2025-12-07 15:07
    Incorrect correct answer in benchmark
  • Issue comment#4Zara7hus7ra2025-12-02 08:41
    About multihop clues
  • Issue comment#11wu-ming2332025-10-21 00:18
    Evaluation details
  • Issue#11wu-ming2332025-10-21 00:18
    Evaluation details
  • Issue comment#9MXueguang2025-10-19 03:42
    Suggestion: Evaluate GPT-OSS with its native browsing tools for a more accurate assessment
  • Issue comment#8MXueguang2025-10-19 03:25
    Add rankllm-based reranker support behind config flag
  • Pull request#10MXueguang2025-10-19 03:24
  • Pull request#7MXueguang2025-09-29 07:26
  • Pull request#7wu-ming2332025-09-28 20:44
  • Pull request#5MXueguang2025-09-03 03:17
  • Issue#3wu-ming2332025-08-23 19:05
    Expanded Source Information
  • Issue comment#3shallinan12025-08-23 05:04
    Expanded Source Information
  • Issue comment#3wu-ming2332025-08-23 04:54
    Expanded Source Information
  • Issue#3shallinan12025-08-21 09:12
    Expanded Source Information
  • Issue#2shallinan12025-08-19 18:15
    Issue Downloading Data
  • Issue comment#1MXueguang2025-08-12 21:24
    Will there be plans to test classic retrievers like e5-base-v2

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 99 stars here means stars gained during the window, not the repo's star count.