LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

MetaMath Mistral 7B by meta-math

 »  All LLMs  »  meta-math  »  MetaMath Mistral 7B   URL Share it on

  5733   

MetaMath Mistral 7B is an open-source language model by meta-math. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, HF Score: 65.8, LLM Explorer Score: 0.15, Arc: 60.7, HellaSwag: 82.6, MMLU: 62, TruthfulQA: 44.9, WinoGrande: 75.8, GSM8K: 68.8.

  Arxiv:2309.12284   Arxiv:2310.06825   Dataset:meta-math/metamathqa   Endpoints compatible   Mistral   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/meta-math/MetaMath-Mistral-7B 

MetaMath Mistral 7B Benchmarks

ARC: 60.67 vs 96.7 (so35)-37.3%
HellaSwag: 82.58 vs 95.3 (gpt4)-13.3%
MMLU: 61.95 vs 88.3 (so35)-29.8%
TruthfulQA: 44.89 vs 59 (gpt4)-23.9%
WinoGrande: 75.77 vs 87.5 (gpt4)-13.4%
GSM8K: 68.84 vs 96.4 (so35)-28.6%
LLME Score: 0.15065
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MetaMath Mistral 7B (meta-math/MetaMath-Mistral-7B)
🌟 Advertise your project 🚀

MetaMath Mistral 7B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
mathematics, AI research
Training Details 
Data Sources:
meta-math/MetaMathQA, GSM8K, MATH
Methodology:
Fine-tuning with adjusted learning rate
Model Architecture:
Mistral-7B
Input Output 
Input Format:
{instruction}
Accepted Modalities:
text
Output Format:
Generated text response
Performance Tips:
Using a smaller learning rate when fine-tuning
LLM NameMetaMath Mistral 7B
Repository 🤗https://huggingface.co/meta-math/MetaMath-Mistral-7B 
Model Size7b
Required VRAM14.4 GB
Updated2026-03-19
Maintainermeta-math
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32001
Torch Data Typebfloat16

Quantized Models of the MetaMath Mistral 7B

Model
Likes
Downloads
VRAM
MetaMath Mistral 7B GGUF101743 GB
MetaMath Mistral 7B GPTQ354 GB
MetaMath Mistral 7B AWQ1104 GB

Best Alternatives to MetaMath Mistral 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
MegaBeam Mistral 7B 512K512K / 14.4 GB844453
SpydazWeb AI HumanAI RP512K / 14.4 GB141
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB808216
Hebrew Mistral 7B 200K256K / 30 GB131615
Astral 256K 7B V2250K / 14.4 GB50
Astral 256K 7B250K / 14.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than meta-math/MetaMath-Mistral-7B.

Rank the MetaMath Mistral 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52392 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer