reasoning benchmark
SimpleQA Leaderboard
SimpleQA is an OpenAI factuality benchmark containing 4,326 short, fact-seeking questions with single, indisputable answers across topics including science, technology, and entertainment.
Updated Sep 7, 2026
Models47
Model coverage47
MetricScore
EvidenceB
SimpleQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelDE | Score97.10% | Percentile100.00% | Participants47 | EvidenceC | Evaluated |
| Rank02 | ModelXA | Score95.00% | Percentile97.83% | Participants47 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Score93.40% | Percentile95.65% | Participants47 | EvidenceC | Evaluated |
| Rank04 | ModelDE | Score92.30% | Percentile93.48% | Participants47 | EvidenceC | Evaluated |
| Rank05 | ModelBA | Score75.00% | Percentile91.30% | Participants47 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score72.10% | Percentile89.13% | Participants47 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score68.70% | Percentile86.96% | Participants47 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score62.50% | Percentile84.78% | Participants47 | EvidenceC | Evaluated |
| Rank09 | ModelDE | Score57.90% | Percentile82.61% | Participants47 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score55.40% | Percentile80.43% | Participants47 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score54.30% | Percentile78.26% | Participants47 | EvidenceC | Evaluated |
| Rank12 | ModelGO | Score54.00% | Percentile76.09% | Participants47 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score51.90% | Percentile73.91% | Participants47 | EvidenceC | Evaluated |
| Rank14 | ModelGO | Score50.80% | Percentile71.74% | Participants47 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score49.60% | Percentile69.57% | Participants47 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score48.00% | Percentile67.39% | Participants47 | EvidenceC | Evaluated |
| Rank17 | ModelOP | Score47.00% | Percentile65.22% | Participants47 | EvidenceC | Evaluated |
| Rank18 | ModelAC | Score44.40% | Percentile63.04% | Participants47 | EvidenceC | Evaluated |
| Rank19 | ModelGO | Score43.30% | Percentile60.87% | Participants47 | EvidenceC | Evaluated |
| Rank20 | ModelOP | Score42.40% | Percentile58.70% | Participants47 | EvidenceC | Evaluated |
| Rank21 | ModelOP | Score38.20% | Percentile56.52% | Participants47 | EvidenceC | Evaluated |
| Rank22 | ModelMA | Score35.30% | Percentile54.35% | Participants47 | EvidenceC | Evaluated |
| Rank23 | ModelDE | Score34.10% | Percentile52.17% | Participants47 | EvidenceC | Evaluated |
| Rank24 | ModelMA | Score31.00% | Percentile50.00% | Participants47 | EvidenceC | Evaluated |
| Rank25 | ModelMA | Score31.00% | Percentile47.83% | Participants47 | EvidenceC | Evaluated |
| Rank26 | ModelDE | Score28.90% | Percentile45.65% | Participants47 | EvidenceC | Evaluated |
| Rank27 | ModelAC | Score27.00% | Percentile43.48% | Participants47 | EvidenceC | Evaluated |
| Rank28 | ModelGO | Score26.90% | Percentile41.30% | Participants47 | EvidenceC | Evaluated |
| Rank29 | ModelDE | Score24.90% | Percentile39.13% | Participants47 | EvidenceC | Evaluated |
| Rank30 | ModelAC | Score23.90% | Percentile36.96% | Participants47 | EvidenceC | Evaluated |
SimpleQA Highlights
The leading models and scores on this benchmark.
SimpleQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SimpleQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is SimpleQA?
What SimpleQA measures and how its scores work.
SimpleQA is a factuality benchmark developed by OpenAI for evaluating large language models.
It measures short-form factual accuracy and model calibration by evaluating whether models know what they know.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SimpleQA
- 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 SimpleQA.
Which model scores highest on SimpleQA?
DeepSeek-V3.2-Exp is currently ranked first with 97.10%.
What are the top three models on SimpleQA?
The current leaders are DeepSeek-V3.2-Exp (97.10%), Grok 4 Fast (95.00%), and DeepSeek-V3.1 (93.40%).
Which SimpleQA model has the lowest official input price?
Gemini 2.5 Flash-Lite has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among SimpleQA results?
The fastest matched records are GPT-4o (132.00 tok/s via OpenAI), Gemini 3 Flash (124.32 tok/s via Google), and o3-mini (115.00 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.