Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
DeepScaleR is a sophisticated language model comprising 1.5 billion parameters, refined from DeepSeek-R1-Distilled-Qwen-1.5B through the use of distributed reinforcement learning combined with an innovative strategy that incrementally expands its context window from 8,000 to 24,000 tokens during the training process. This model was developed using approximately 40,000 meticulously selected mathematical problems sourced from high-level competition datasets, including AIME (1984–2023), AMC (pre-2023), Omni-MATH, and STILL. Achieving an impressive 43.1% accuracy on the AIME 2024 exam, DeepScaleR demonstrates a significant enhancement of around 14.3 percentage points compared to its base model, and it even outperforms the proprietary O1-Preview model, which is considerably larger. Additionally, it excels on a variety of mathematical benchmarks such as MATH-500, AMC 2023, Minerva Math, and OlympiadBench, indicating that smaller, optimized models fine-tuned with reinforcement learning can rival or surpass the capabilities of larger models in complex reasoning tasks. This advancement underscores the potential of efficient modeling approaches in the realm of mathematical problem-solving.
Description
A versatile JavaScript display engine designed for mathematics, ensuring compatibility across all web browsers. It delivers stunning and accessible mathematical content seamlessly, eliminating any setup requirements for users—MathJax operates effortlessly. This powerful tool enables the conversion of conventional print materials into contemporary, web-friendly formats and ePubs. The dedicated MathJax team offers training sessions for your staff, focusing on how to leverage our resources for developing online educational materials and crafting accessible STEM content. Additionally, MathJax's flexibility allows customization according to your institution's specific needs, including personalized configurations and tailored software workflows. Utilizing CSS with web fonts or SVG instead of bitmap images or Flash, MathJax ensures that equations are scalable alongside surrounding text at any zoom level. Its modular design supports various input formats like MathML, TeX, and ASCIImath, while generating outputs in HTML+CSS, SVG, or MathML. Furthermore, MathJax is compatible with screen readers and enhances user experience through features like expression zoom and interactive exploration, making it an invaluable resource for educators and students alike.
API Access
Has API
No
API Access
Has API
No
Integrations
Eurekos
No
MarkSnip
No
MathML Kit
No
Pricing Details
Free
Free Trial
No
Free Version
Yes
Pricing Details
Free
Free Trial
No
Free Version
Yes
Deployment
Web-Based
No
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
Yes
iPad App
Yes
Android App
Yes
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
Yes
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
Yes
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
Agentica Project
Founded
2025
Country
United States
Website
agentica-project.com
Vendor Details
Company Name
MathJax
Founded
2009
Country
United States
Website
www.mathjax.org