InfiniteBench/En.QA

long context official site →

Multilingual: no

InfiniteBench English Question Answering variant - first LLM benchmark featuring average data length surpassing 100K tokens for evaluating long-context capabilities with 12 tasks spanning diverse domains

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: long_context. Language: en. Verified by llm-stats: no.