{
  "id": "swe-rebench",
  "name": "SWE-rebench",
  "category": "information",
  "summary": "Nebius's continuously refreshed, decontaminated SWE agent benchmark and dataset: 21,000+ validated GitHub issue-PR tasks plus a time-windowed leaderboard.",
  "description": "The Hugging Face dataset `nebius/SWE-rebench` (CC-BY-4.0; each task also carries its source repo's license) is built by an automated pipeline that extracts and validates interactive tasks from 3,400+ Python repositories, with prebuilt Docker images for thousands of tasks. The leaderboard at swe-rebench.com evaluates models and agents on fresh tasks within a selectable time window to limit contamination and reports resolved rate, pass@5, cost and tokens per problem. A SWE-rebench v2 (paper arXiv 2602.23866) is also published. Run evaluations with the MIT-licensed SWE-bench fork.",
  "url": "https://swe-rebench.com",
  "repo": "https://github.com/SWE-rebench/SWE-bench-fork",
  "docs": "https://huggingface.co/datasets/nebius/SWE-rebench",
  "tags": [
    "benchmark",
    "dataset",
    "coding-agents",
    "leaderboard"
  ],
  "license": "CC-BY-4.0",
  "pricing": "free",
  "status": "active",
  "related": [
    "swe-bench",
    "swe-gym",
    "swe-smith"
  ],
  "sources": [
    "https://swe-rebench.com",
    "https://huggingface.co/datasets/nebius/SWE-rebench",
    "https://github.com/SWE-rebench/SWE-bench-fork",
    "https://github.com/SWE-rebench/SWE-rebench-V2"
  ],
  "added": "2026-10-25",
  "updated": "2026-10-25",
  "last_verified": "2026-10-25",
  "submitted_by": "agentica-curator",
  "maintainer": "Nebius",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/swe-rebench/",
    "markdown": "https://indexagentica.com/entries/swe-rebench.md",
    "json": "https://indexagentica.com/api/entries/swe-rebench.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/swe-rebench.json"
  }
}