MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models on Mobile Application Development

• URL: http://arxiv.org/abs/2603.24946v1
• Date: Thu, 26 Mar 2026 02:31:03 GMT
• Title: MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models on Mobile Application Development
• Abstract summary: We introduce MobileDev-Bench, a benchmark comprising 384 real-world issue-resolution tasks collected from 18 production mobile applications spanning Android Native (Java/Kotlin), React Native (TypeScript), and Flutter (Dart)<n>Each task pairs an authentic developer-reported issue with executable test patches, enabling fully automated validation of model-generated fixes within mobile build environments.<n> Evaluation of four state-of-the-art code-capable LLMs, GPT- 5.2, Claude Sonnet 4.5, Gemini Flash 2.5, and Qwen3-Coder, yields low end-to-end resolution rates of 3.39%
• Score: 1.4302803674538154
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on general-purpose libraries or web applications, leaving mobile application development largely unexplored despite its strict platform constraints, framework-driven lifecycles, and complex platform API interactions. We introduce MobileDev-Bench, a benchmark comprising 384 real-world issue-resolution tasks collected from 18 production mobile applications spanning Android Native (Java/Kotlin), React Native (TypeScript), and Flutter (Dart). Each task pairs an authentic developer-reported issue with executable test patches, enabling fully automated validation of model-generated fixes within mobile build environments. The benchmark exhibits substantial patch complexity: fixes modify 12.5 files and 324.9 lines on average, and 35.7% of instances require coordinated changes across multiple artifact types, such as source and manifest files. Evaluation of four state-of-the-art code-capable LLMs, GPT- 5.2, Claude Sonnet 4.5, Gemini Flash 2.5, and Qwen3-Coder, yields low end-to-end resolution rates of 3.39%-5.21%, revealing significant performance gaps compared to prior benchmarks. Further analysis reveals systematic failure modes, with fault localization across multi-file and multi-artifact changes emerging as the primary bottleneck.

Related papers

• BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents [38.39627583261406]
  We present BlueLM-GUI, a 35B-A3B mobile GUI agent built as a real-device-centric flywheel.<n>Every Sample Matters: a dual-track pipeline with Heterogeneous Triple-System Consensus evaluation and an Error Correction & Derivation Module.<n>Every Rollout Is Real: a three-stage recipe---continual pre-training, supervised fine-tuning, and agentic reinforcement learning on hundreds of real phones.
  arXiv  Detail & Related papers  (2026-09-11T03:36:35Z)
• AppEval: A Unified Benchmark for LLM-Based Mobile Application Repair in ArkTS, Swift, and Kotlin [25.775485279136763]
  AppEval is a benchmark and native-toolchain evaluation framework for mobile application repair.<n>We present AppEval, a benchmark and native-toolchain evaluation framework for mobile application repair across HarmonyOS/ArkTS, iOS/Swift, and Android/Kotlin.
  arXiv  Detail & Related papers  (2026-08-19T06:30:34Z)
• SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information [61.41881137371855]
  We introduce SPIEval, a benchmark for large language models (LLMs)<n> SPIEval comprises 250 tasks spanning 4,335 personal records distributed across 10 apps and supports multi-turn interaction through 21 tools.<n>The best-performing model, GPT-5.5 (xhigh), achieves only 57.3% accuracy, while the weakest achieves just 16.4%.
  arXiv  Detail & Related papers  (2026-08-11T09:14:53Z)
• HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents [57.53434680014667]
  HyMobileAgent is a vision-native foundation model built on Hy3.0-VL-A3B.<n>We develop a joint data and environment centric scaling framework to address the key bottlenecks of mobile interaction.
  arXiv  Detail & Related papers  (2026-07-16T04:12:42Z)
• MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents [50.27505102982638]
  We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents.<n>The framework provides a stateful execution environment spanning 500+ tools across 16 application domains.<n>It supports multi-image, multi-turn tasks where agents must ground progressively arriving visual inputs into executable tool calls.
  arXiv  Detail & Related papers  (2026-07-13T17:13:09Z)
• PhoneWorld: Scaling Phone-Use Agent Environments [101.288508963127]
  PhoneWorld is a reusable pipeline that converts real GUI trajectories and screenshots into controllable phone-use environments.<n>It builds runnable mock Android apps backed by read-only app content and mutable state.<n>It covers 34 apps across 16 domains, spanning common consumer mobile behaviors such as search, browsing, shopping, booking, media, and social interaction.
  arXiv  Detail & Related papers  (2026-05-28T07:14:15Z)
• SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies [0.764671395172401]
  SWE-WebDev Bench is a 68-metric evaluation framework spanning 25 primary and 43 diagnostic metrics across seven groups.<n>Our evaluation reveals four recurring shortcomings in the current generation of AI app builders.
  arXiv  Detail & Related papers  (2026-05-06T08:30:37Z)
• AndroidLens: Long-latency Evaluation with Nested Sub-targets for Android GUI Agents [36.66219528445988]
  We introduce AndroidLens, a challenging evaluation framework for mobile GUI agents.<n>It comprises 571 long-latency tasks in both Chinese and English environments.<n>Our evaluation indicates that even the best models reach only a 12.7% task success rate and 50.47% ATP.
  arXiv  Detail & Related papers  (2025-12-24T17:40:42Z)
• One Battle After Another: Probing LLMs' Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework [51.50565654314582]
  Large language models can follow users' instructions throughout a dialogue spanning multiple topics.<n>Existing benchmarks are often limited to a fixed number of turns, making them susceptible to saturation and failing to account for the user's interactive experience.<n>We propose a framework for assessing multi-turn instruction-following ability.
  arXiv  Detail & Related papers  (2025-11-05T14:39:59Z)
• MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning [91.90342432541138]
  Scaling up model size and training data has advanced foundation models for instance-level perception.<n>High computational cost limits adoption on resource-constrained platforms.<n>We introduce a new benchmark for efficient segmentation on both high-performance computing platforms and mobile devices.
  arXiv  Detail & Related papers  (2025-10-16T18:00:00Z)
• ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks [37.79008306764891]
  Real-world tasks are often complex and allow for multiple valid solutions.<n> offline benchmarks can only validate a single predefined "golden path"<n>Online dynamic testing is constrained by the complexity and non-reproducibility of real devices.<n>This paper introduces a novel graph-structured benchmarking framework.
  arXiv  Detail & Related papers  (2025-10-16T12:30:05Z)
• AppForge: From Assistant to Independent Developer - Are GPTs Ready for Software Development? [28.63033734662797]
  APPFORGE is a benchmark consisting of 101 software development problems drawn from real-world Android apps.<n>We design a multi-agent system to automatically summarize the main functionalities from app documents and navigate the app to synthesize test cases.<n>Following rigorous manual verification by Android development experts, APPFORGE incorporates the test cases within an automated evaluation framework.
  arXiv  Detail & Related papers  (2025-10-09T03:26:05Z)
• SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
  We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
  arXiv  Detail & Related papers  (2025-05-29T18:28:02Z)
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents [58.18100825673032]
  This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions.<n>In the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively)
  arXiv  Detail & Related papers  (2025-01-21T17:48:10Z)
• BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning [1.9854146581797698]
  BLAZE is an approach that employs dynamic chunking and hard example learning.<n>It fine-tunes a GPT-based model using challenging bug cases to enhance cross-project and cross-language bug localization.<n>BLAZE achieves up to an increase of 120% in Top 1 accuracy, 144% in Mean Average Precision (MAP), and 100% in Mean Reciprocal Rank (MRR)
  arXiv  Detail & Related papers  (2024-07-24T20:44:36Z)
• BigIssue: A Realistic Bug Localization Benchmark [89.8240118116093]
  BigIssue is a benchmark for realistic bug localization. We provide a general benchmark with a diversity of real and synthetic Java bugs. We hope to advance the state of the art in bug localization, in turn improving APR performance and increasing its applicability to the modern development cycle.
  arXiv  Detail & Related papers  (2022-07-21T20:17:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.