What it measures
- Factuality
- Short-answer knowledge
- Hallucination resistance
SimpleQA Verified
A factuality benchmark for short-answer factual knowledge questions.
How to read the score
% correct; higher is better.
Sourced Ranking
| Rank | Model | Provider | Score | Source | Source Type | Verified |
|---|
Limitations
- Factuality scores should be separated from broad reasoning scores.
- The arXiv paper is static; Kaggle is the operational source.
- Google DeepMind points to Kaggle for dataset, eval, and leaderboard entry.
leaderboard
Kaggle SimpleQA Verified benchmark page
The arXiv paper is static; Kaggle is the operational source. Google DeepMind points to Kaggle for dataset, eval, and leaderboard entry.
paper
SimpleQA Verified paper or specification
Use for benchmark definition, not necessarily for latest model scores.
official
SimpleQA Verified dataset or code
Use for dataset, code, or implementation details; score freshness depends on the benchmark.
leaderboard
Kaggle OpenAI SimpleQA benchmark page
Related SimpleQA benchmark page from OpenAI. Do not merge SimpleQA and SimpleQA Verified rows without explicit labeling.