Dataset · allenai
OpenBookQA: open book questions
allenai/openbookqa
English QA benchmark with questions requiring multi-step reasoning and general knowledge.
What's inside
A set of questions in English for testing text comprehension and reasoning. Questions require multiple reasoning steps, the use of additional general and common-sense knowledge, and dense text understanding. Each question is accompanied by open book facts.
What you can do with it
- Evaluating question-answering models
- Testing multi-step reasoning
- Fine-tuning models on QA pairs
- Tasks
- Question answering
- Languages
- English
- Size
- 10K–100K rows
- Downloads this month
- 162.9K
- Likes
- 162
Models trained on it
- jaredpalmer/kev-27bText classification 3.5K
- mradermacher/kev-27b-GGUFMultiple choice 1.7K
- mradermacher/Dolphy-1.0-i1-GGUF 750
- ReckonerLabs/Pascaline-3MText generation 645
- mradermacher/Dolphy-1.0-GGUF 526
- littlemex/prismyra-decision-qwen3.6-35b-a3b-fp8-36lText classification 321
- littlemex/prismyra-decision-qwen3.6-35b-a3b-nvfp4-36lText classification 245
- whittleOrg/Whittle-Reflex-25B-A3BZero shot classification 134
How to load it
from datasets import load_dataset
ds = load_dataset("allenai/openbookqa")