VIBE-Pro
A repo-level code generation and full-project delivery benchmark spanning web, mobile, and simulation-style implementation tasks.
1 models
Higher is better.
- 1MiniMax M2.7MiniMax55.6
About this benchmark
- Metric
- Repository-level implementation benchmark
- Tasks
- Full project delivery tasks
- Authors
- MiniMax (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.