--- source: 'https://howaiworks.ai/blog/h-company-holo3-desktop-agent' section: blog title: 'Holo3: H Company''s SOTA Foundation Model for Desktop Agents' description: >- H Company unveils Holo3, a high-performance Mixture-of-Experts model family that sets a new industry standard for autonomous desktop application control. date: '2026-04-02' author: HowAIWorks Team tags: - AI - h-company - holo3 - Agents - desktop-automation - MoE - gui-agents - osworld - Automation readingTime: 4 minutes --- # Holo3: H Company's SOTA Foundation Model for Desktop Agents > H Company unveils Holo3, a high-performance Mixture-of-Experts model family that sets a new industry standard for autonomous desktop application control. ## Introduction The race for truly autonomous AI agents has reached a new milestone with the release of **Holo3**, a state-of-the-art family of multimodal models designed by the Paris-based startup **H Company** (formerly Holistic AI). Built specifically for the complex task of controlling graphical user interfaces (GUIs), Holo3 represents a significant leap forward in bridge-to-action technology, allowing AI to navigate desktop environments as a human would. H Company, led by Stanford researcher **Charles Kantor** and Google DeepMind veteran **Laurent Sifre** (a key contributor to the AlphaGo project), has quickly become a powerhouse in the European AI scene. With a massive $220 million seed round backed by investors like Eric Schmidt, Amazon, Samsung, and UiPath, the company is positioning Holo3 as the foundational infrastructure for the next generation of business automation. ## Architecture: The Mixture-of-Experts Advantage Holo3 is built on a **Mixture-of-Experts (MoE)** architecture, which allows the model to handle diverse and specialized tasks without the computational overhead of traditional dense models. The family consists of two primary versions: - **Holo3-122B-A10B (The Flagship)**: This high-capacity model is the current SOTA leader. It is available exclusively through H Company's platform, priced at $0.40 per million input tokens and $3.00 per million output tokens. - **Holo3-35B-A3B (The Open Version)**: Released under the **Apache 2.0 license**, this model is available on Hugging Face. It offers a more accessible entry point for developers, with a free Inference API tier (limited to 10 PRM) and a paid tier at $0.25/$1.80 per million tokens. ## Three-Stage Training Loop What sets Holo3 apart is its rigorous training methodology. H Company utilized a **closed-loop system** consisting of three distinct phases to ensure the model can handle real-world unpredictability: 1. **Synthetic Navigation Generation**: The model starts by learning from high-quality, synthetic examples of interface navigation based on predefined scenarios. 2. **Expansion Beyond Initial Conditions**: To prevent overfitting and prepare the model for "edge cases," the synthetic data is expanded to include non-standard situations and unexpected UI behaviors. 3. **Curated Selection and RL**: Finally, all training examples undergo a curated selection process and are refined through Reinforcement Learning (RL) to optimize for success rates and safety. To support this massive undertaking, H Company developed a proprietary "Corporate Environment Generator," where agents build entire web applications from scratch, creating a playground of verifiable tasks for the model to master. ## Performance: Breaking Benchmarks The flagship Holo3-122B-A10B model has already claimed the top spot on the **OSWorld-Verified** benchmark, scoring a record-breaking **78.85%**. This benchmark is widely considered the most rigorous test for desktop interaction, requiring the model to solve multi-step problems across various operating systems and applications. H Company also introduced the **H Corporate Benchmarks**, featuring 486 multi-step tasks across four critical business categories: - **E-commerce**: Handling complex purchasing and logistics workflows. - **Business Software**: Interacting with ERPs and CRMs. - **Collaboration Tools**: Coordinating across project management suites. - **Cross-App Scenarios**: The "Holy Grail" of agents, requiring synchronization between multiple systems simultaneously (e.g., extracting data from a PDF, matching it against a budget in Excel, and sending automated emails in Outlook). ## Conclusion Holo3 isn't just an improvement over existing models; it is a specialized tool built for a future where AI handles the "busy work" of desktop computing. By combining a powerhouse MoE architecture with a sophisticated synthetic training environment, H Company has moved us closer to a world where agents can seamlessly navigate the software we use every day. ## Sources - [H Company Official Website](https://www.hcompany.ai/holo3) - [Holo3-35B-A3B on Hugging Face](https://huggingface.co/Hcompany/Holo3-35B-A3B) - [OSWorld Benchmark Leaderboard](https://os-world.github.io/) --- _Ready to explore the future of agentic AI? Dive into our [glossary](https://howaiworks.ai/glossary) to learn more about Mixture-of-Experts and GUI agents._ ## Frequently Asked Questions ### What is Holo3? Holo3 is a family of multimodal models from H Company designed specifically to navigate and control graphical user interfaces (GUIs) across desktop environments. ### Is Holo3 available for public use? Yes. The Holo3-35B-A3B model is open-sourced under the Apache 2.0 license on Hugging Face, while the flagship 122B version is accessible via H Company's platform. ### How does Holo3 compare to other desktop agents? Holo3-122B-A10B currently ranks #1 on the OSWorld-Verified benchmark with a score of 78.85%, making it the leading model for desktop-based tasks. --- Source: https://howaiworks.ai/blog/h-company-holo3-desktop-agent — HowAIWorks.ai