InfiniteBench

Usage load with datasets from datasets import load_dataset, Features, Value, Sequence # Define the features schema ft = Features({ "id": Value("int64"), "context": Value("string"), "input": Value("string"), "answer": Sequence(Value("string")), "options": Sequence(Value("string")) }) # Load the dataset with the specifie

Papers using InfiniteBench (7)

AllMem: A Memory-centric Recipe for Efficient Long-context Modeling2026MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training2025QwenLong-CPRS: Towards infty-LLMs with Dynamic Context Optimization2025Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation2025Does RAG Really Perform Bad For Long-Context Processing?2025RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding2025Why Does the Effective Context Length of LLMs Fall Short?2024 · 1 cites