Audience
Researchers, students, and developers interested in an AI model capable of mathematical reasoning and logic tasks without requiring heavy hardware
About DeepScaleR
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.
Other Popular Alternatives & Related Software
DeepSeekMath
DeepSeekMath is a specialized 7B parameter language model developed by DeepSeek-AI, designed to push the boundaries of mathematical reasoning in open-source language models. It starts from the DeepSeek-Coder-v1.5 7B model and undergoes further pre-training with 120B math-related tokens sourced from Common Crawl, alongside natural language and code data. DeepSeekMath has demonstrated remarkable performance, achieving a 51.7% score on the competition-level MATH benchmark without external tools or voting techniques, closely competing with the likes of Gemini-Ultra and GPT-4. The model's capabilities are enhanced by a meticulous data selection pipeline and the introduction of Group Relative Policy Optimization (GRPO), which optimizes both mathematical reasoning and memory usage. DeepSeekMath is available in base, instruct, and RL versions, supporting both research and commercial use, and is aimed at those looking to explore or apply advanced mathematical problem-solving in AI contexts.
Learn more about DeepSeekMath
Phi-4-reasoning
Phi-4-reasoning is a 14-billion parameter transformer-based language model optimized for complex reasoning tasks, including math, coding, algorithmic problem solving, and planning. Trained via supervised fine-tuning of Phi-4 on carefully curated "teachable" prompts and reasoning demonstrations generated using o3-mini, it generates detailed reasoning chains that effectively leverage inference-time compute. Phi-4-reasoning incorporates outcome-based reinforcement learning to produce longer reasoning traces. It outperforms significantly larger open-weight models such as DeepSeek-R1-Distill-Llama-70B and approaches the performance levels of the full DeepSeek-R1 model across a wide range of reasoning tasks. Phi-4-reasoning is designed for environments with constrained computing or latency. Fine-tuned with synthetic data generated by DeepSeek-R1, it provides high-quality, step-by-step problem solving.
Learn more about Phi-4-reasoning
Phi-4-mini-reasoning
Phi-4-mini-reasoning is a 3.8-billion parameter transformer-based language model optimized for mathematical reasoning and step-by-step problem solving in environments with constrained computing or latency. Fine-tuned with synthetic data generated by the DeepSeek-R1 model, it balances efficiency with advanced reasoning ability. Trained on over one million diverse math problems spanning multiple levels of difficulty from middle school to Ph.D. level, Phi-4-mini-reasoning outperforms its base model on long sentence generation across various evaluations and surpasses larger models like OpenThinker-7B, Llama-3.2-3B-instruct, and DeepSeek-R1. It features a 128K-token context window and supports function calling, enabling integration with external tools and APIs. Phi-4-mini-reasoning can be quantized using Microsoft Olive or Apple MLX Framework for deployment on edge devices such as IoT, laptops, and mobile devices.
Learn more about Phi-4-mini-reasoning
Phi-4-reasoning-plus
Phi-4-reasoning-plus is a 14-billion parameter open-weight reasoning model that builds upon Phi-4-reasoning capabilities. It is further trained with reinforcement learning to utilize more inference-time compute, using 1.5x more tokens than Phi-4-reasoning, to deliver higher accuracy. Despite its significantly smaller size, Phi-4-reasoning-plus achieves better performance than OpenAI o1-mini and DeepSeek-R1 at most benchmarks, including mathematical reasoning and Ph.D. level science questions. It surpasses the full DeepSeek-R1 model (with 671 billion parameters) on the AIME 2025 test, the 2025 qualifier for the USA Math Olympiad. Phi-4-reasoning-plus is available on Azure AI Foundry and HuggingFace.
Learn more about Phi-4-reasoning-plus
Pricing
Starting Price:
Free
Free Version:
Free Version available.
Integrations
No integrations listed.
Company Information
Agentica Project
Founded: 2025
United States
agentica-project.com
Videos and Screen Captures
Other Useful Business Software
Our Free Plans just got better! | Auth0
You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
Product Details
Platforms Supported
Windows
Mac
Linux
On-Premises
Training
Documentation
Support
Online
DeepScaleR Frequently Asked Questions
Q: What kinds of users and organization types does DeepScaleR work with?
DeepScaleR works with these users and organization types: Mid Size Business, Small Business, Enterprise, Freelance, Nonprofit, Government, and Startup.
Q: What languages does DeepScaleR support in their product?
DeepScaleR supports these languages: English.
Q: What kind of support options does DeepScaleR offer?
DeepScaleR offers support via online.
Q: What type of training does DeepScaleR provide?
DeepScaleR provides training in the form of documentation.
Q: How much does DeepScaleR cost?
Pricing for DeepScaleR starts at Free.
