# GameDevBench: Evaluating Agentic Capabilities Through Game Development

arXiv: https://arxiv.org/abs/2602.11103 · HTML: https://mlsanity.com/paper/2602.11103/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [Action-Conditional Video Prediction using Deep Networks in Atari Games](https://mlsanity.com/paper/1507.08750/) (2015)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [MarioGPT: Open-Ended Text2Level Generation through Large Language Models](https://mlsanity.com/paper/2302.05981/) (2023)
- [SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding](https://mlsanity.com/paper/2410.11761/) (2024)
- [Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning](https://mlsanity.com/paper/2601.11109/) (2026)
- [SIMA 2: A Generalist Embodied Agent for Virtual Worlds](https://mlsanity.com/paper/2512.04797/) (2025)
- [FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation](https://mlsanity.com/paper/2506.13832/) (2025)
- [Pok'eChamp: an Expert-level Minimax Language Agent](https://mlsanity.com/paper/2503.04094/) (2025)
- [EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits](https://mlsanity.com/paper/2511.04486/) (2025)
- [Multi-Actor Generative Artificial Intelligence as a Game Engine](https://mlsanity.com/paper/2507.08892/) (2025)

## Built on by (most cited first, 28 of 28)

- [GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?](https://mlsanity.com/paper/2606.17861/) (2026)
- [Code World Model: Coding Agent as World Brain](https://mlsanity.com/paper/2608.25927/) (2026)
- [WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis](https://mlsanity.com/paper/2606.01869/) (2026)
- [GameEngineBench: Evaluating Coding Agents on Real C++ Runtime Environments](https://mlsanity.com/paper/2607.03525/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?](https://mlsanity.com/paper/2608.21833/) (2026)
- [SceneActBench: Can Agents Act on the 3D Scenes They See?](https://mlsanity.com/paper/2607.22393/) (2026)
- [The Verifier is the Curriculum: Precision Sets the Return on Search in Code Self-Distillation](https://mlsanity.com/paper/2607.09709/) (2026)
- [Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models](https://mlsanity.com/paper/2608.25518/) (2026)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions](https://mlsanity.com/paper/2609.21562/) (2026)
- [GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development](https://mlsanity.com/paper/2609.21293/) (2026)
- [PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides](https://mlsanity.com/paper/2609.29718/) (2026)
- [RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement](https://mlsanity.com/paper/2609.39045/) (2026)
- [VibeJam: A User Study Platform for Web Development with Agents](https://mlsanity.com/paper/2608.29889/) (2026)
- [Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization](https://mlsanity.com/paper/2609.18996/) (2026)
- [GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents](https://mlsanity.com/paper/2609.22308/) (2026)
- [CraftBench-UE: Deterministic Evaluation for Coding Agents in Unreal Engine](https://mlsanity.com/paper/2609.23142/) (2026)
- [CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering](https://mlsanity.com/paper/2609.32600/) (2026)
- [SWE-Game: Can Coding Agents Build the Games We Want?](https://mlsanity.com/paper/2609.33678/) (2026)
- [A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?](https://mlsanity.com/paper/2609.39564/) (2026)
- [OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game Engine](https://mlsanity.com/paper/2610.02563/) (2026)
- [Spec2Game: Can LLMs Generate Complete Playable Games from Detailed Specifications?](https://mlsanity.com/paper/2610.04253/) (2026)
- [GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets](https://mlsanity.com/paper/2610.06910/) (2026)
- [Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness](https://mlsanity.com/paper/2610.08621/) (2026)
- [SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications](https://mlsanity.com/paper/2610.15708/) (2026)
- [Game-Creation-Agents: Autonomous Game Production](https://mlsanity.com/paper/2610.16776/) (2026)
- [Player-1: Learning to Play from Synthetic Experience](https://mlsanity.com/paper/2610.20584/) (2026)

## Abstract (arXiv)

Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. In game development, agents must navigate large, dense codebases while manipulating intrinsically multimodal assets such as shaders, sprites, and animations within a visual game scene. We present GameDevBench, the first benchmark for evaluating agents on game development tasks. GameDevBench consists of 333 tasks derived from web and video tutorials. Tasks require significant multimodal understanding and are complex: the average solution requires over three times the lines of code and file changes compared to prior software development benchmarks. Agents struggle with game development, with the best agent and method solving only 53.8% of tasks. We find a strong correlation between perceived task difficulty and multimodal complexity, with average success rate dropping from 51.4% on gameplay-oriented tasks to 33.0% on 2D graphics tasks. To improve multimodal capability, we introduce two simple image- and video-based feedback mechanisms for agents. Despite their simplicity, these methods consistently improve performance, increasing GPT-5.4's performance from 41.1% to 52.0% when given visual feedback.