Skip to content

GraphRAG-Bench/GraphRAG-Benchmark

View on GitHub ↗Related repositories →

The official repo of GraphRAG-Bench for evaluating GraphRAG models. "When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation". (ICLR'26)

active 2025-05-162026-06-14 (UTC)

Partial coverage11,770 / 13,089 hourly files (90%) · 2 absent upstream · 1,316 failed, retryable2025-02-112026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
328
Pushes
51
Pull requests
14
Issues
24
Stars
189
Forks
15

Activity over time

Daily event counts in the loaded window

Line chart, 395 days from 2025-05-16 to 2026-06-14. Pushes: 51 total, peak 4 in a day. Pull requests: 14 total, peak 3 in a day. Issues: 24 total, peak 4 in a day. Comments: 25 total, peak 5 in a day. Stars: 189 total, peak 6 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

  • Issue#517HHHHH2025-12-19 09:11
    Regarding graph quality
  • Pull request#48SherryChen01142025-12-12 17:11
  • Pull request#47chriscain8282025-12-11 04:36
  • Issue#42Qing1452025-12-03 08:40
    Direct response results of llm
  • Issue comment#38Eric-Xiang-5262025-12-01 02:11
    [Data Discrepancy] Reproduced graph metrics for HippoRAG2 (Medical Dataset) conflict with paper's reported statistics
  • Issue comment#42Eric-Xiang-5262025-11-30 02:39
    Direct response results of llm
  • Issue#30Qing1452025-11-30 00:52
    How long does benchmarking take for you?
  • Issue#44xiaotao442025-11-29 07:45
    是否可以用DIGIMON跑所有bench
  • Issue#377HHHHH2025-11-24 04:42
    Questions about the weighting of answer accuracy
  • Issue comment#377HHHHH2025-11-24 04:42
    Questions about the weighting of answer accuracy
  • Pull request#35Freaking-Bob2025-11-20 20:18
  • Pull request#33ZhizhenChen2025-11-18 05:58
  • Pull request#33ZhizhenChen2025-11-18 05:54
  • Pull request#32ujisoo2025-11-18 05:35
  • Issue comment#31yishanyuan2025-11-18 00:35
    Yishanyuan 1
  • Issue comment#31yishanyuan2025-11-18 00:34
    Yishanyuan 1
  • Issue comment#30Eric-Xiang-5262025-11-15 02:30
    How long does benchmarking take for you?
  • Issue#28Eric-Xiang-5262025-10-30 02:23
    Error embedding url while using ollama
  • Issue comment#27cxfyxl2025-10-16 04:44
    table 9中LightRAG复现实验的问题
  • Issue#22Qing1452025-10-16 03:24
    Redundancy in Example code
  • Issue#27cxfyxl2025-10-16 03:14
    table 9中LightRAG复现实验的问题
  • Issue#267HHHHH2025-10-15 07:14
    About the novel dataset
  • Issue comment#23Eric-Xiang-5262025-10-06 03:14
    Cant run fast-graphrag
  • Issue comment#24Eric-Xiang-5262025-10-06 03:14
    Cant run hipporag
  • Issue comment#21Powerkrieger2025-09-29 09:48
    separate generation and evaluation instructions into their own README…

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 189 stars here means stars gained during the window, not the repo's star count.