Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Description

Holo4 is H Company's series of generalist computer-use and agentic AI models built to perform multi-step work across software interfaces. It is available as Holo4 27B, a dense 27-billion-parameter model, and Holo4 35B-A3B, a Mixture-of-Experts model containing 35 billion total parameters with 3 billion active. Holo4 can interact with applications by clicking and typing through graphical interfaces, writing and executing code, or calling MCP and API tools. The same model can operate across desktops, websites, Android devices, code sandboxes, and business APIs without requiring developers to select a separate specialized model for each environment. H Company trained Holo4 using 127 billion supervised fine-tuning tokens, with approximately three-quarters consisting of successful agentic trajectories spanning desktop, web, MCP/API, and mobile tasks. Reinforcement learning then trained separate experts for desktop and web interaction and for terminal, MCP, and API work before merging them into a single model. Holo4 27B scored 85.2% on OSWorld, 61.7% on OSWorld 2.0, 45.4% on AutomationBench, and 85.1% on AndroidWorld in the evaluations reported by H Company. The models support a 256K context window, with the 27B model positioned for greater accuracy on long multi-step tasks and the 35B-A3B version positioned as a faster and less expensive alternative. Holo4 is available through a hosted API and downloadable model weights, enabling developers and enterprises to build agents that perform workflows spanning multiple applications and interaction methods.

Description

Qwen2.5-Max is an advanced Mixture-of-Experts (MoE) model created by the Qwen team, which has been pretrained on an extensive dataset of over 20 trillion tokens and subsequently enhanced through methods like Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF). Its performance in evaluations surpasses that of models such as DeepSeek V3 across various benchmarks, including Arena-Hard, LiveBench, LiveCodeBench, and GPQA-Diamond, while also achieving strong results in other tests like MMLU-Pro. This model is available through an API on Alibaba Cloud, allowing users to easily integrate it into their applications, and it can also be interacted with on Qwen Chat for a hands-on experience. With its superior capabilities, Qwen2.5-Max represents a significant advancement in AI model technology.

API Access

Has API Yes 

API Access

Has API Yes 

Screenshots View All

Screenshots View All

Integrations

Amp Yes 
ChatGPT Yes 
ChatGPT Enterprise Yes 
ChatGPT Images Yes 
ChatGPT Pro Yes 
ChatGPT Work Yes 
Cursor Yes 
Dart Yes 
Hugging Face No 
Microsoft 365 Copilot Yes 
Microsoft Excel Yes 
Node.js Yes 
OpenAI Yes 
Perplexity Computer Yes 
PowerShell Yes 
TranslateAI Yes 
Vercel AI Gateway Yes 
Visual Studio Code Yes 
Wazzap AI Yes 
YAML Yes 

Integrations

Amp No 
ChatGPT No 
ChatGPT Enterprise No 
ChatGPT Images No 
ChatGPT Pro No 
ChatGPT Work No 
Cursor No 
Dart No 
Hugging Face Yes 
Microsoft 365 Copilot No 
Microsoft Excel No 
Node.js No 
OpenAI No 
Perplexity Computer No 
PowerShell No 
TranslateAI No 
Vercel AI Gateway No 
Visual Studio Code No 
Wazzap AI No 
YAML No 

Pricing Details

$0.40 per 1M tokens (input)
Input: $0.40 per 1 million tokens
Output: $3 per 1 million tokens
Free Trial No 
Free Version No 

Pricing Details

Free
Open source
Free Trial No 
Free Version Yes 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows Yes 
Mac Yes 
Linux Yes 
Chromebook No 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support Yes 

Customer Support

Business Hours No 
Live Rep (24/7) No 
Online Support No 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person No 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person No 

Vendor Details

Company Name

H Company

Founded

2023

Country

France

Website

openai.com

Vendor Details

Company Name

Alibaba

Founded

1999

Country

China

Website

qwenlm.github.io/blog/qwen2.5-max/

Product Features

Alternatives

No Alternatives

Alternatives

ERNIE 4.5 Reviews

ERNIE 4.5

Baidu
DeepSeek R2 Reviews

DeepSeek R2

DeepSeek
Qwen 4 Reviews

Qwen 4

Alibaba
ERNIE X1 Reviews

ERNIE X1

Baidu