Skip to content
#

benchmark

Star

Here are 4,434 public repositories matching this topic...

Language: All
Filter by language
All 4,434 Python 914 Go 356 C++ 345 JavaScript 327 Java 301 C# 217 C 215 Jupyter Notebook 183 Rust 162 Shell 159
Sort: Recently updated
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

Psycoy / MixEval

Star 1

MixEval, a ground-truth-based dynamic benchmark derived from off-the-shelf benchmark mixtures, which evaluates LLMs with a highly capable model ranking (i.e., 0.96 correlation with Chatbot Arena) while running locally and quickly (6% the time and cost of running MMLU), with its queries being stably updated every month to avoid contamination.

benchmark machine-learning deep-learning evaluation benchmarking-suite evaluation-framework benchmarking-framework foundation-models large-language-models large-language-model llm-training llm-inference llm-evaluation large-multimodal-models llm-evaluation-framework benchmark-mixture dynamic-benchmark
  • Updated Jun 1, 2024
  • Python

Improve this page

Add a description, image, and links to the benchmark topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the benchmark topic, visit your repo's landing page and select "manage topics."

Learn more