DeepScaleRAgentica Project
|
Open R1Open R1
|
|||||
| DeepScaleR | Open R1 | |||||
|---|---|---|---|---|---|---|
Related Products
|
||||||
DeepScaleR:
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.
|
Open R1:
About
Open R1 is a community-driven, open-source initiative aimed at replicating the advanced AI capabilities of DeepSeek-R1 through transparent methodologies. You can try Open R1 AI model or DeepSeek R1 free online chat on Open R1.
The project offers a comprehensive implementation of DeepSeek-R1's reasoning-optimized training pipeline, including tools for GRPO training, SFT fine-tuning, and synthetic data generation, all under the MIT license. While the original training data remains proprietary, Open R1 provides the complete toolchain for users to develop and fine-tune their own models.
|
|||||
DeepScaleR:
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
|
Open R1:
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
|
|||||
DeepScaleR:
Audience
Researchers, students, and developers interested in an AI model capable of mathematical reasoning and logic tasks without requiring heavy hardware
|
Open R1:
Audience
Developers, teams, researchers, general users
|
|||||
DeepScaleR:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Open R1:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
DeepScaleR:
API
Offers API
Not Supported
|
Open R1:
API
Offers API
Not Supported
|
|||||
DeepScaleR:
Screenshots and Videos |
Open R1:
Screenshots and VideosNo images available
|
|||||
DeepScaleR:
Pricing
Free
Free Version
Supported
Free Trial
Not Supported
|
Open R1:
Pricing
Free
Open source
Free Version
Supported
Free Trial
Not Supported
|
|||||
DeepScaleR:
Reviews/
|
Open R1:
Reviews/
|
|||||
DeepScaleR:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Open R1:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
DeepScaleR:
Company InformationAgentica Project
Founded: 2025
United States
agentica-project.com
|
Open R1:
Company InformationOpen R1
Founded: 2025
United Kingdom
open-r1.com
|
|||||
DeepScaleR:
Alternatives |
Open R1:
Alternatives |
|||||
|
DeepScaleR:
|
Open R1:
|
|||||
|
DeepScaleR:
|
Open R1:
|
|||||
|
DeepScaleR:
|
Open R1:
|
|||||
|
DeepScaleR:
|
Open R1:
|
|||||
DeepScaleR:
Categories |
Open R1:
Categories |
|||||
DeepScaleR:
Integrations
No info available.
|
Open R1:
Integrations
No info available.
|
|||||
|
DeepScaleR:
|
Open R1:
|