# Evaluating my own model on AGIEval or MMLU benchmarks

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fevaluating-my-own-model-on-agieval-or-mmlu-benchmarks%2F63451%3E%5C
**Category:** Beginners\
**Created:** [November 24, 2023, 9:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fevaluating-my-own-model-on-agieval-or-mmlu-benchmarks%2F63451 "2023-11-24T21:28:25Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![allyc](https://avatars.discourse-cdn.com/v4/letter/a/73ab20/32.png) [@allyc](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fallyc)%5C
**Post date:** [November 24, 2023, 9:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fevaluating-my-own-model-on-agieval-or-mmlu-benchmarks%2F63451%2F1 "2023-11-24T21:28:25Z")

</div>

I have recently trained from scratch a GPT-2 model. I now want to evaluate its performance on two popular benchmarks that assess the general intelligence of a model: AGIEval and MMLU. How do I do this?