Coding benchmark
VIBE-Pro leaderboard
Every model the catalog carries a published VIBE-Pro value for, ranked by that value.
CategoryCoding
MeasureRepository-level implementation benchmark
TasksFull project delivery tasks
DifficultyEnd-to-end software delivery
Published byMiniMax M2.7: Early Echoes of Self-Evolution
A repo-level code generation and full-project delivery benchmark spanning web, mobile, and simulation-style implementation tasks.
VIBE-Pro ranking
1 model with a published VIBE-Pro value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Repository-level implementation benchmark |
|---|---|---|---|
| 1 |  MiniMax M2.7 | MiniMax | 55.6 |
Evidence key: Observed
Rows are ordered by the value MiniMax M2.7: Early Echoes of Self-Evolution published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.