Skip to Main Content
Trunchbull
Not yet importedRequires sandbox

SWE-bench Verified

Upstream publisher Princeton NLPSWE-bench/SWE-bench

A human-validated set of real GitHub issues requiring repository patches that pass tests.

codeagentssandboxrepositories
PROVENANCEUPSTREAM RECORD
Upstream source
SWE-bench/SWE-bench
Trunchbull port
Not packaged
Version
VERIFIED / 500
Release digest
Not compiled
License
MIT
Source commit: verified-500Published Indexed July 26, 2026

WHAT THIS PROJECT MEASURES

README

SWE-bench Verified evaluates whether an agent can understand an issue, navigate a real repository, produce a patch, and pass the relevant tests.

Trunchbull indexes the upstream project but does not yet maintain a runnable port. Each case needs an immutable repository snapshot, task-specific environment, patch capture, and test verifier.

EXECUTION CONTRACT

Requires repository checkout, containerized execution, patch capture, and test grading.

TRUNCHBULL AVAILABILITY

Import status

Not yet imported

Trunchbull has not ported this project yet. A port must package repositories, environments, and test-based verification into immutable releases.

2 CASES

Evaluation cases

2

swe-bench/django-11001

Django issue #11001

Requires sandbox

Inspect a pinned repository and produce a testable patch.

sandbox.filessandbox.commands

swe-bench/sympy-13031

SymPy issue #13031

Requires sandbox

Repair symbolic behavior in a pinned source checkout.

sandbox.filessandbox.commands

2 REQUESTED TOOLS

Tools

2

sandbox.files

sandbox

Reads and modifies the pinned repository checkout.

Required

sandbox.commands

sandbox

Runs repository tests and captures verifier evidence.

Required

MACHINE-READABLE PROVENANCE

Registry record

{
  "name": "SWE-bench Verified",
  "catalogOwner": null,
  "source": {
    "url": "https://github.com/SWE-bench/SWE-bench",
    "version": "Verified · 500 cases",
    "commit": "verified-500",
    "license": "MIT"
  },
  "port": null,
  "release": {
    "digest": "Not compiled",
    "lane": "sandbox",
    "sandboxRequired": true
  },
  "cases": [
    "swe-bench/django-11001",
    "swe-bench/sympy-13031"
  ],
  "tools": [
    "sandbox.files",
    "sandbox.commands"
  ]
}

BUILD ON THIS PROJECT

Build and run supported benchmarks in your workspace.

Sign up