AppSim-Bench

What is AppSim-Bench?

Controllable simulated apps for mobile GUI agent evaluation, containing 557 tasks across 17 Chinese and English apps with deterministic backend data and…

Released

2026-09-07

Evaluates

Agents & Tool Use, General AI, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.07712

AppSim-Bench paper and code

• Paper https://arxiv.org/abs/2609.07712
• Code https://github.com/Acrab-Agentic-Labs/AppSim

Which sources cite AppSim-Bench?

• AppSim-Bench

Related Agents & Tool Use, General AI, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench
• ActiveSciBench