Benchmark

VIBE Benchmark

What is VIBE?

Visual Interface Building Evaluation benchmark for UI/app generation. Benchmark Radar tracks 1 reported scores for VIBE, cited by 1 source documents.

Modality
text
Evaluates
code
Openness
unknown
Importer
LLM Stats
Reported scores
1

Source provenance

VIBE results and reported scores

LLM Stats

ModelOrganizationReported valueReportedEvidence
MiniMax M2.1MiniMax0.8862025-12-23evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite VIBE?

Related code benchmarks