Benchmark

WebDev Arena Benchmark

What is WebDev Arena?

WebDev Arena is a leaderboard for evaluating AI models on web development tasks, including zero-shot generation, complex prompts, and interactive web UI…

Modality
text
Evaluates
reasoning, frontend development, code
Openness
unknown
Importer
LLM Stats
Reported scores
1

Source provenance

WebDev Arena results and reported scores

LLM Stats

ModelOrganizationReported valueReportedEvidence
Gemini 3.7 FlashGoogle1588.02026-08-13evidence

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 WebDev Arena?

Related reasoning, frontend development, code benchmarks