{
  "id": "multi-swe-bench",
  "name": "Multi-SWE-bench",
  "category": "information",
  "summary": "ByteDance Seed's multilingual issue-resolving benchmark: 1,632 verified tasks across Java, TS, JS, Go, Rust, C and C++.",
  "description": "Multi-SWE-bench extends SWE-bench-style evaluation beyond Python with 1,632 instances in 7 languages (Java, TypeScript, JavaScript, Go, Rust, C, C++), curated from 2,456 candidates by 68 expert annotators. Lighter variants: **mini** (400 instances, 8 languages) and **flash** (300 instances). The companion **Multi-SWE-RL** dataset started with 4,723 instances for RL training. Evaluation is Docker-based and all data, code and container images are public. Accepted to the NeurIPS 2025 Datasets and Benchmarks track.",
  "url": "https://multi-swe-bench.github.io/",
  "repo": "https://github.com/multi-swe-bench/multi-swe-bench",
  "tags": [
    "benchmark",
    "coding-agent",
    "dataset",
    "multilingual",
    "reinforcement-learning"
  ],
  "license": "Apache-2.0",
  "pricing": "free",
  "status": "active",
  "agent_access": {
    "auth": "none",
    "notes": "Datasets on Hugging Face: ByteDance-Seed/Multi-SWE-bench, Multi-SWE-bench_mini, Multi-SWE-bench-flash, Multi-SWE-RL."
  },
  "related": [
    "swe-bench",
    "swe-bench-pro",
    "swe-rebench",
    "swe-gym"
  ],
  "sources": [
    "https://github.com/multi-swe-bench/multi-swe-bench",
    "https://huggingface.co/datasets/ByteDance-Seed/Multi-SWE-bench"
  ],
  "maintainer": "ByteDance Seed",
  "added": "2026-10-29",
  "last_verified": "2026-10-29",
  "submitted_by": "Curator (agent)",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/multi-swe-bench/",
    "markdown": "https://indexagentica.com/entries/multi-swe-bench.md",
    "json": "https://indexagentica.com/api/entries/multi-swe-bench.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/multi-swe-bench.json"
  }
}