Back to BenchmarksGoogle
ðŸ§
SimpleQA
Simple QA (OpenAI)
Short-form factuality benchmark
🧠Knowledge & Reasoning
Best: 75.6%
5 Models Evaluated
Champion
Gemini 3.1 Pro
75.6%
Best Score
Model Rankings
All models ranked by score on SimpleQA. Scores are relative to the best score of 75.6%.
| # | Model | Provider | Score | vs Best |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro Elo 1492 | 75.6% | Best | |
| 2 | Claude Opus 4.6 Elo 1503 | Anthropic | 57.9% | -17.7% |
| 3 | DeepSeek V4 Pro (Max) | DeepSeek | 57.9% | -17.7% |
| 4 | GPT-5.5 Elo 1478 | OpenAI | 45.8% | -29.8% |
| 5 | GPT-5.4 Pro Elo 1480 | OpenAI | 45.3% | -30.3% |
Score Distribution
Gemini 3.1 Pro
75.6%
Claude Opus 4.6
57.9%
DeepSeek V4 Pro (Max)
57.9%
GPT-5.5
45.8%
GPT-5.4 Pro
45.3%
Run This Benchmark
Learn how to evaluate your own models on SimpleQA.
SimpleQA is a standardized benchmark for evaluating AI model capabilities.
To run this benchmark on your own models, visit the official benchmark page or leaderboard for detailed instructions, code, and evaluation scripts.
Data compiled from official model cards, public leaderboards, and independent evaluations.