DeepScaleR

DeepScaleR

Agentica Project
+
+

Related Products

  • CoachIQ
    45 Ratings
    Visit Website
  • PathSolutions TotalView
    43 Ratings
    Visit Website
  • Procare
    3,575 Ratings
    Visit Website
  • Canditech
    111 Ratings
    Visit Website
  • AlisQI
    108 Ratings
    Visit Website
  • LeaseAccounting.app
    Visit Website
  • Rise Vision
    1,540 Ratings
    Visit Website
  • Total ETO
    46 Ratings
    Visit Website
  • Numa
    14 Ratings
    Visit Website
  • CirrusPrint
    2 Ratings
    Visit Website

About

Beast Academy is a full math program from Art of Problem Solving for kids ages 6–13, designed to teach problem solving and logical thinking by covering grade-level standards in greater depth than other elementary math curricula. It presents mathematics as a beautiful, creative discipline through challenging problems, engaging explanations, visual reasoning, and a focus on the hows and whys of math. Beast Academy Online is an interactive learning platform for advanced young problem solvers, with full access to Levels 1–5 of the curriculum, over 1,000 lessons, more than 20,000 practice problems, interactive puzzles, games, instructional videos, and online access to the comic-style Beast Academy Guide books. The books make up a complete curriculum for aspiring math beasts, using captivating comic book lessons and Practice books filled with problems ranging from introductory exercises to very challenging puzzles and word problems.

About

DeepScaleR is a 1.5-billion-parameter language model fine-tuned from DeepSeek-R1-Distilled-Qwen-1.5B using distributed reinforcement learning and a novel iterative context-lengthening strategy that gradually increases its context window from 8K to 24K tokens during training. It was trained on ~40,000 carefully curated mathematical problems drawn from competition-level datasets like AIME (1984–2023), AMC (pre-2023), Omni-MATH, and STILL. DeepScaleR achieves 43.1% accuracy on AIME 2024, a roughly 14.3 percentage point boost over the base model, and surpasses the performance of the proprietary O1-Preview model despite its much smaller size. It also posts strong results on a suite of math benchmarks (e.g., MATH-500, AMC 2023, Minerva Math, OlympiadBench), demonstrating that small, efficient models tuned with RL can match or exceed larger baselines on reasoning tasks.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Supported
Mac Supported
Linux Supported
Cloud Not Supported
On-Premises Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

Elementary students who need a rigorous, puzzle-based math curriculum that develops deep problem-solving and logical thinking

Audience

Researchers, students, and developers interested in an AI model capable of mathematical reasoning and logic tasks without requiring heavy hardware

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Not Supported

API

Offers API Not Supported

Screenshots and Videos

Screenshots and Videos

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Pricing

Free
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

Beast Academy
United States
beastacademy.com

Company Information

Agentica Project
Founded: 2025
United States
agentica-project.com

Alternatives

IXL

IXL

IXL Learning

Alternatives

DeepCoder

DeepCoder

Agentica Project
HIX Tutor

HIX Tutor

HIX.AI
Phi-4-reasoning

Phi-4-reasoning

Microsoft
Athene-V2

Athene-V2

Nexusflow

Categories

K-12 Supported

Categories

AI Models Supported

Integrations

No info available.

Integrations

No info available.
Claim Beast Academy and update features and information
Claim Beast Academy and update features and information
Claim DeepScaleR and update features and information
Claim DeepScaleR and update features and information