∞Bench: En.QA (English Question Answering)

∞Bench's open-ended English QA split: answer a free-text question after reading a novel averaging around 193K tokens, scored by token-level F1 against the reference answer.

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorylong-context
Subcategorylong-document open-ended question answering over English novels
Page statusactive
MetricF1 (token-level, SQuAD-style, against the reference answer)
Directionhigher_is_better
Unit%
Dataset size351
Dataset licenceMIT, per the OpenBMB/InfiniteBench GitHub repository; see the infinitebench family page.
PublisherDepartment of Computer Science and Technology, Tsinghua University

What it measures

Given a full English novel (averaging about 192,600 tokens of context) and a question that requires aggregating scattered details (for example, a running total) or filtering out one specific fact among many similar candidates, the model produces a short free-text answer rather than choosing among options, as En.MC does. Questions come from the same human annotation pipeline as En.MC, and the reference prompt instructs the model to answer concisely, so the task combines long-range retrieval-and-reasoning with the separate demand of producing a short, precisely matched answer rather than a discursive one.

Task format

Open-ended, free-text question answering over a long document, with generation capped at a short number of output tokens; scored automatically against a reference answer rather than by an LLM judge.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub