textScaleAI/SWE-bench_Proswe-benchcoding-agentsbenchmarkevaluationsoftware-engineeringscale-aiagentslong-horizoncodellm-eval

SWE-bench Pro

Category
Text
Records
731 rows
Format
PARQUET
Update Frequency
One-time snapshot
Collection Method
uploaded
PII
None detected
File Size
~7.45 MB
Downloads
3

About this data

Enterprise-level benchmark dataset from Scale AI for evaluating AI agents on long-horizon software engineering tasks. Follows SWE-Bench Verified structure with challenging real-world coding problems.

Schema

NameTypeDescription
repoVARCHARRepository owner and name (e.g., 'NodeBB/NodeBB')
instance_idVARCHARUnique identifier for the task instance combining repo, commit hash, and variant
base_commitVARCHARGit commit hash representing the initial state before the fix
patchVARCHARUnified diff format showing the complete solution changes required
test_patchVARCHARUnified diff format for test file modifications needed to validate the fix
problem_statementVARCHARNatural language description of the software engineering issue to resolve
requirementsVARCHARSpecific constraints, dependencies, or implementation requirements for the task
interfaceVARCHARAPI signatures, function definitions, or class interfaces that must be implemented
repo_languageVARCHARPrimary programming language of the repository (e.g., 'JavaScript', 'Python')
fail_to_passVARCHARTest identifiers or commands that must transition from failing to passing state
pass_to_passVARCHARTest identifiers or commands that must remain passing throughout the solution
issue_specificityVARCHARCategorical level describing precision of the problem scope (e.g., 'high', 'medium')
issue_categoriesVARCHARComma-separated tags classifying issue type (e.g., 'bug', 'feature', 'refactor')
before_repo_set_cmdVARCHARShell command(s) to execute setup or initialization in the repository context
selected_test_files_to_runVARCHARComma-separated paths to test files used for validating the solution
dockerhub_tagVARCHARDocker image reference specifying environment and dependencies for evaluation

Sample Data

Preview a sample of the data before downloading.

Free

Open dataset

Quality: No ratings
3 downloads
Seller: DataBazaar
Sign up to download

Agent? No sign-up needed →

For AI Agents

Via MCP Server
# 1. Add to your agent's MCP config (claude_desktop_config.json or similar):
{
  "mcpServers": {
    "databazaar": { "command": "npx", "args": ["databazaar-mcp"] }
  }
}

# 2. Your agent can then call:
search_datasets({ query: "SWE-bench Pro" })
// Found: de2141e6-1a79-421b-a389-801739457e65
get_download_url({ dataset_id: "de2141e6-1a79-421b-a389-801739457e65" })  // free — no API key needed
Via REST API
# Free dataset — no API key required:
curl https://api.databazaar.io/datasets/de2141e6-1a79-421b-a389-801739457e65/download-url