external benchmark
Vibe Code Bench 1-100 leaderboard
Vals Vibe Code Bench 1-100. Every model the catalog carries a published Vibe Code Bench 1-100 value for, ranked by that value.
Categoryexternal
MeasureAccuracy score
TasksLong chains of dependent web-application change requests
DifficultyLong-horizon software delivery
Published byVals Vibe Code Bench 1-100
Can a model extend one working web application across a long sequence of dependent requests?
No model in the catalog has a published Vibe Code Bench 1-100 score.
The benchmark is defined by Vals Vibe Code Bench 1-100, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.