reasoning benchmark
PopQA Leaderboard
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 17, 2026
Models3
Model coverage3
MetricScore
EvidenceB
PopQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelIB | Score26.2% | Percentile100.0% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelIB | Score26.2% | Percentile50.0% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelIB | Score22.9% | Percentile0.0% | Participants3 | EvidenceC | Evaluated |
PopQA Highlights
The leading models and scores on this benchmark.
PopQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for PopQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis popqa AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01IB
- Score
- 26.2%
- Speed
- Up to 50 tok/s via Replicate
Strengths
- Ranks #1 of 3 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures PopQA, not total model capability
- 02
- Score
- 26.2%
- Speed
- Up to 50 tok/s via Replicate
Strengths
- Ranks #2 of 3 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures PopQA, not total model capability
- 03
- Score
- 22.9%
Strengths
- Ranks #3 of 3 compared models
- 0th percentile on this benchmark
- C evidence result
Considerations
- This result measures PopQA, not total model capability
Selection summary
Best AI Models for PopQA
Granite 3.3 8B Base currently leads PopQA with 26.2%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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.