MobileForge Benchmark

What is MobileForge?

A benchmark that tests whether multimodal LLMs can turn multi-screen mobile app designs into buildable projects with working navigation.

Released

2026-05-29

Evaluates

General AI, Robotics & Embodied AI, cs.HC

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.28645

MobileForge paper and code

• Paper https://arxiv.org/abs/2607.28645
• Code https://github.com/anoa12159-hue/mobileforge_eval

Which sources cite MobileForge?

• MobileForge

Related General AI, Robotics & Embodied AI, cs.HC benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 4DSynth-Nav
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ABC-Bench