The Qodo Code Review Benchmark 1.0 is a large-scale evaluation dataset designed to measure AI-powered code review systems. It consists of 100 real, merged pull requests sourced from production-grade open-source repositories across multiple languages, into which 580... The dataset was created by Qodo and last updated on February 3, 2026.
Use Cases
- Benchmark AI code review systems based on realistic pull request scenarios
- Evaluate AI performance across multiple programming languages based on the TypeScript, Python, JavaScript, C, C#, Rust, and Swift examples
- Train models for automated code review based on real, merged pull requests
Strengths
- Contains 100 real, merged pull requests from production-grade repositories
- Includes examples across multiple languages: TypeScript, Python, JavaScript, C, C#, Rust, and Swift
- Designed specifically for large-scale evaluation of AI systems
Limitations
- Column-level documentation is absent; field semantics must be inferred after download
- Row count is unknown, which may limit suitability assessment
- Description metadata is limited; actual data quality requires manual inspection after download
Provenance
- Source
- Qodo
- Collection Method
- Sourced from production-grade open-source repositories
- Freshness
- Last updated 2026-02-03 19:01:08; freshness should be verified