Skip to content

⌘ K

🚀 Quick Start

Introduction
Installation
Basic Usage
Parameters
Supported Datasets

🔧 User Guides

Evaluation Backends
- OpenCompass
- VLMEvalKit
- RAGEval
Model Inference Stress Testing
Arena Mode

🛠️ Advanced Tutorials

Mixed Data Evaluation
Adding Benchmark Evaluation
Custom Datasets
Custom Model

🧰 Third-Party Tools

ToolBench
LongBench-Write

🧪 Benchmarking Results

Benchmarking
- MMLU
Speed Benchmarking
- QwQ-32B-Preview

📖 Best Practices

ms-swift Integration
Full-Chain LLM Training

🌟 Blogs

Welcome to the EvalScope Blogs!
- RAG Evaluation Survey: Framework, Metrics, and Methods

/

Benchmarking

Benchmarking#

Here are the benchmarking results for some models:

MMLU

LongBench-Write

© 2022-2024, Alibaba ModelScope Built with Sphinx 8.1.3