Eval

Show value of an importable object

Like `typing._eval_type`, but lets older Python versions use newer typing features.

HuggingFace community-driven open-source library of evaluation

Safely evaluate AST nodes without side effects

A simple, safe single expression evaluator library.

Safe, minimalistic evaluator of python expression using ast module

Validation and secure evaluation of untrusted python expressions

Microsoft Azure Evaluation Library for Python

Framework for evaluating stochastic code execution, especially code making use of LLMs

Universal library for evaluating AI models

The LLM Evaluation Framework

A framework for evaluating language models

Evalica, your favourite evaluation toolkit.

Testing framework for sequence labeling

A getattr and setattr that works on nested objects, lists, dicts, and any combination thereof without resorting to eval

MS-COCO Caption Evaluation for Python 3

LLM Evaluations

EvalScope: Lightweight LLMs Evaluation Framework

Provides Python bindings for popular Information Retrieval measures implemented within trec_eval.

Limited evaluator

Open-source evaluators for LLM applications

"EvalPlus for rigourous evaluation of LLM-synthesized code"

Python Mathematical Expression Evaluator

A library for providing a simple interface to create new metrics and an easy-to-use toolkit for metric computations and checkpointing.

The WxO evaluation framework

an AutoML library that builds, optimizes, and evaluates machine learning pipelines using domain-specific objective functions

A poker hand evaluation and equity calculation library

Faster interpretation of the original COCOEval

Use EvalAI through command line interface

Evaluation tools for the SIGSEP MUS database

AlpacaEval : An Automatic Evaluator of Instruction-following Models

Common metrics for common audio/music processing tasks.

evalutils helps users create extensions for grand-challenge.org

A custom Streamlit component to evaluate arbitrary Javascript expressions.

A framework for evaluating language models - packaged by NVIDIA

Evaluating and scoring financial data

Provides Python bindings for popular Information Retrieval measures implemented within trec_eval.

Open-source evaluators for LLM agents

In-loop evaluation tasks for language modeling

Backwards-compatibility package for API of trulens_eval<1.0.0 using API of trulens-*>=1.0.0.

eval-mm is a tool for evaluating Multi-Modal Large Language Models.

Package for fast computation of BSS Eval metrics for source separation

A lightweight and configurable evaluation package

Serialization based on ast.literal_eval

clusteval is a python package for unsupervised cluster validation.

EM algorithms for integrated spatial and spectral models.