# OpenBookQA

> A science question-answering benchmark that tests whether models can apply a small open-book set of elementary science facts to multi-step reasoning questions.

Canonical page: https://benchlm.ai/benchmarks/openbookqa

- Category: [Knowledge](/knowledge)
- Last updated: September 27, 2026

## About OpenBookQA

- Year: 2018
- Tasks: Elementary science questions
- Format: 4-way multiple choice
- Difficulty: Elementary science reasoning
- Paper: [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://arxiv.org/abs/1809.02789)

OpenBookQA was designed to test grounded science reasoning rather than pure memorization. Each question is paired with a core science fact, but models still need additional commonsense knowledge to infer the correct answer.

OpenBookQA is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (0 models)

Benchmark data for this page is coming soon.

## FAQ

### What does OpenBookQA measure?

A science question-answering benchmark that tests whether models can apply a small open-book set of elementary science facts to multi-step reasoning questions.

### Which model scores highest on OpenBookQA?

No models have been evaluated on OpenBookQA yet.

### How many models are evaluated on OpenBookQA?

0 AI models have been evaluated on OpenBookQA on BenchLM.

### Does OpenBookQA affect BenchLM's overall score?

Not directly. OpenBookQA is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.