reasoning benchmark
PopQA
PopQA is an entity-centric open-domain question-answering dataset consisting of 14,000 QA pairs designed to evaluate language models' ability to memorize and recall factual knowledge across entities with varying popularity levels. The dataset probes both parametric memory (stored in model parameters) and non-parametric memory effectiveness, with questions covering 16 diverse relationship types from Wikidata converted to natural language using templates. Created by sampling knowledge triples from Wikidata and converting them to natural language questions, focusing on long-tail entities to understand LMs' strengths and limitations in memorizing factual knowledge.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
PopQA Ranking
Higher score ranks better on this benchmark.
| 01 | IB | 26.2% | 100.0% | 3 | C | |
| 02 | IB | 26.2% | 50.0% | 3 | C | |
| 03 | IB | 22.9% | 0.0% | 3 | C |
PopQA Score Distribution
A closer view of the leading scores on this benchmark.
PopQA Highlights
The leading models and scores on this benchmark.
What is PopQA?
What PopQA measures and how its scores work.
PopQA is an entity-centric open-domain question-answering dataset consisting of 14,000 QA pairs designed to evaluate language models' ability to memorize and recall factual knowledge across entities with varying popularity levels. The dataset probes both parametric memory (stored in model parameters) and non-parametric memory effectiveness, with questions covering 16 diverse relationship types from Wikidata converted to natural language using templates. Created by sampling knowledge triples from Wikidata and converting them to natural language questions, focusing on long-tail entities to understand LMs' strengths and limitations in memorizing factual knowledge.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PopQA
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- popqa|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about PopQA.
Which model scores highest on PopQA?
Granite 3.3 8B Base is currently ranked first with 26.2%.
What does PopQA measure?
PopQA is an entity-centric open-domain question-answering dataset consisting of 14,000 QA pairs designed to evaluate language models' ability to memorize and recall factual knowledge across entities with varying popularity levels. The dataset probes both parametric memory (stored in model parameters) and non-parametric memory effectiveness, with questions covering 16 diverse relationship types from Wikidata converted to natural language using templates. Created by sampling knowledge triples from Wikidata and converting them to natural language questions, focusing on long-tail entities to understand LMs' strengths and limitations in memorizing factual knowledge.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.