Benchmarks/code/VIBE

VIBE

Visual Interface Building Evaluation benchmark for UI/app generation

Progress Over Time

Interactive timeline showing model performance evolution on VIBE

State-of-the-art frontier
Open
Proprietary

VIBE Leaderboard

1 models
ContextCostLicense
1
MiniMax
MiniMax M2.1
MiniMax
230B1.0M$0.30 / $1.20
Notice missing or incorrect data?

FAQ

Common questions about VIBE

Visual Interface Building Evaluation benchmark for UI/app generation
The VIBE leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, MiniMax M2.1 by MiniMax leads with a score of 0.886. The average score across all models is 0.886.
The highest VIBE score is 0.886, achieved by MiniMax M2.1 from MiniMax.
1 models have been evaluated on the VIBE benchmark, with 0 verified results and 1 self-reported results.
VIBE is categorized under code. The benchmark evaluates text models.

Sub-benchmarks

VIBE-Pro

VIBE-Pro is an advanced version of the VIBE (Visual & Interactive Benchmark for Execution) benchmark that evaluates LLMs on professional-grade full-stack application development tasks. It measures model performance across complex real-world development scenarios including web, mobile, and backend applications with higher difficulty than the standard VIBE benchmark.

text•Max 1