reasoning benchmark
OpenBookQA Leaderboard
OpenBookQA is a question-answering dataset of 5,957 multiple-choice, elementary-level science questions based on 1,326 core science facts.
Updated Sep 5, 2026
Models5
Model coverage5
MetricScore
EvidenceB
OpenBookQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score89.60% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score79.20% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelMI | Score79.20% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score60.60% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelNR | Score49.40% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
OpenBookQA Highlights
The leading models and scores on this benchmark.
OpenBookQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for OpenBookQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is OpenBookQA?
What OpenBookQA measures and how its scores work.
OpenBookQA is a benchmark modeled after open book exams that assesses human understanding through elementary-level science questions.
It measures performance using Score, reported as a ratio, on questions requiring application of science facts to novel situations and multi-hop reasoning with broad common knowledge.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OpenBookQA
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about OpenBookQA.
Which model scores highest on OpenBookQA?
Phi-3.5-MoE-instruct is currently ranked first with 89.60%.
What are the top three models on OpenBookQA?
The current leaders are Phi-3.5-MoE-instruct (89.60%), Phi-3.5-mini-instruct (79.20%), and Phi 4 Mini (79.20%).
Which OpenBookQA model has the lowest official input price?
Phi 4 Mini has the lowest matched official input price at $0.08 input / $0.30 output per 1M tokens.
Which models are fastest among OpenBookQA results?
The fastest matched records are Mistral NeMo Instruct (42.00 tok/s via Google) and Phi-3.5-mini-instruct (23.00 tok/s via Azure).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.