OpenMOSS/LongLLaDA

[AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs

31
/ 100
Emerging

This project helps AI researchers and practitioners evaluate how well large language models (LLMs) can handle very long texts. It takes different LLM architectures and various long-context benchmarks (like "Needle-In-A-Haystack" or RULER) as input, and outputs performance metrics and comparisons related to an LLM's ability to understand or retrieve information from extensive documents. It's designed for those who develop, benchmark, or work with advanced language models, particularly focusing on diffusion LLMs.

Use this if you are researching or developing large language models and need to rigorously test their performance with exceptionally long input contexts.

Not ideal if you are an end-user looking for a pre-built application or a simple API to process long documents without needing to benchmark LLM architectures.

Large Language Models AI Research LLM Benchmarking Context Window Extension Natural Language Processing
No License No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 7 / 25
Community 10 / 25

How are scores calculated?

Stars

53

Forks

5

Language

Python

License

Last pushed

Dec 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/OpenMOSS/LongLLaDA"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.