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 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
PopQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | IB | 26.2% | 100.0% | 3 | C | |
| 2 | IB | 26.2% | 50.0% | 3 | C | |
| 3 | IB | 22.9% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
PopQA highlights
The top published results on this benchmark's own scale.
What is PopQA?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- PopQA
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- popqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.