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

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

In honor of Archimedes, whose 2311th anniversary we celebrate this year, we are excited to introduce our inaugural Mathstral model, a specialized 7B architecture tailored for mathematical reasoning and scientific exploration. This model features a 32k context window and is released under the Apache 2.0 license. Our intention behind contributing Mathstral to the scientific community is to enhance the pursuit of solving advanced mathematical challenges that necessitate intricate, multi-step logical reasoning. The launch of Mathstral is part of our wider initiative to support academic endeavors, developed in conjunction with Project Numina. Much like Isaac Newton during his era, Mathstral builds upon the foundation laid by Mistral 7B, focusing on STEM disciplines. It demonstrates top-tier reasoning capabilities within its category, achieving remarkable results on various industry-standard benchmarks. Notably, it scores 56.6% on the MATH benchmark and 63.47% on the MMLU benchmark, showcasing the performance differences by subject between Mathstral 7B and its predecessor, Mistral 7B, further emphasizing the advancements made in mathematical modeling. This initiative aims to foster innovation and collaboration within the mathematical community.

API Access

Has API No 

API Access

Has API Yes 

Screenshots View All

Screenshots View All

Integrations

AlphaCorp No 
Deep Infra No 
EvalsOne No 
Groq No 
Hugging Face No 
HumanLayer No 
Ministral 3B No 
Mistral AI No 
Mistral Large No 
Mistral NeMo No 
Mixtral 8x7B No 
NexalAI No 
Nutanix Enterprise AI No 
OpenPipe No 
Pipeshift No 
Pixtral Large No 
Respan No 
SydeLabs No 
Toolmark No 
thisorthis.ai No 

Integrations

AlphaCorp Yes 
Deep Infra Yes 
EvalsOne Yes 
Groq Yes 
Hugging Face Yes 
HumanLayer Yes 
Ministral 3B Yes 
Mistral AI Yes 
Mistral Large Yes 
Mistral NeMo Yes 
Mixtral 8x7B Yes 
NexalAI Yes 
Nutanix Enterprise AI Yes 
OpenPipe Yes 
Pipeshift Yes 
Pixtral Large Yes 
Respan Yes 
SydeLabs Yes 
Toolmark Yes 
thisorthis.ai Yes 

Pricing Details

Free
Free Trial No 
Free Version Yes 

Pricing Details

Free
Open source
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 No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Customer Support

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

Customer Support

Business Hours No 
Live Rep (24/7) Yes 
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

Mistral AI

Founded

2023

Country

France

Website

mistral.ai/news/mathstral/

Product Features

Alternatives

Alternatives

Solar Pro 2 Reviews

Solar Pro 2

Upstage AI
DeepCoder Reviews

DeepCoder

Agentica Project
Mistral Large 2 Reviews

Mistral Large 2

Mistral AI
Claude Opus 3 Reviews

Claude Opus 3

Anthropic
Phi-4-reasoning Reviews

Phi-4-reasoning

Microsoft
Mistral NeMo Reviews

Mistral NeMo

Mistral AI