LLM Reference

MetaMath Llemma 7B

Released
2023-10-27
Last refreshed
2026-05-19
Status
Researched 16d ago

MetaMath Llemma 7B has model metadata, but missing tracked provider pricing keeps it from being a default production pick.

Use it for

  • Teams evaluating general LLM work

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
MetaMath
Released
2023-10-27
Parameters
7B
Architecture
Decoder Only
Specialization
general
Training
finetuned
Created by

AI models focused on mathematics and proofs

N/A
Founded N/A
Website
Pricing

No tracked provider token pricing is available yet.

About

MetaMath-Llemma-7B is a fine-tuned large language model designed specifically for mathematical reasoning, building upon the Llemma-7B architecture. It showcases notably enhanced performance over similar-sized open-source models in solving mathematical problems, thanks to a novel question bootstrapping method that enriches its training data with diverse mathematical questions. Trained on the comprehensive MetaMathQA dataset, which is derived from GSM8K and MATH benchmarks, the model achieves impressive scores: Pass@1 scores of 69.2% on GSM8K and 30.0% on MATH. Despite its achievements, it remains outperformed by closed-source models like GPT-4, pointing to avenues for further improvement. Additionally, its reliance on datasets augmented with tools like ChatGPT 3.5 may introduce certain biases. Nevertheless, its open-source nature allows for ongoing research and improvements by the AI community.

MetaMath Llemma 7B is a model in the MetaMath family. No headline benchmark score is tracked for MetaMath Llemma 7B yet.

Top use-case fit

No primary decision-task fit is mapped for this model yet.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Rankings & picks(5)