analytics

Improve LLMs with deepeval

Name: Improve LLMs with deepeval
Author: confident-ai

Get reliable evaluation metrics for your language models with deepeval, used by founders, backed by 17k+ GitHub stars

17,589 stars1,798 forksPythonHealth Score 9/10Updated 8/13/2026100% free · open source

What it does

Deepeval provides reliable evaluation metrics for language models, allowing founders to assess their model's performance accurately.

Install / run

pip install deepeval

When to use it

•When you need to compare the performance of different language models
•When you want to evaluate your language model's performance on a specific task or dataset
•When you need to identify areas for improvement in your language model

Quick start

1 Clone the deepeval repository using `git clone https://github.com/confident-ai/deepeval.git`
2Navigate to the deepeval directory using `cd deepeval`
3Install the required dependencies using `pip install -r requirements.txt`
4 Run the example evaluation script using `python examples/eval_example.py`
5Configure your evaluation task by modifying the `tasks.json` file

Ready-to-paste prompt

python -m deepeval.examples.eval_example --model-name bert-base-uncased --task-name sentiment-analysis --dataset-name imdb

Heads up: Deepeval requires the `transformers` library, which can be installed using `pip install transformers`, and also requires a GPU with at least 8 GB of VRAM for large-scale evaluations

Saves to your device