SimpleQA: leaderboard
SimpleQA: Evaluates broad language-model knowledge, reasoning, commonsense, instruction following, or exam-style accuracy.
Metric: SimpleQA (%). Source: openai.com. Source: benchmarklist.com. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5-Base | 36 | |
| 2 | GLM-5.3-Flash-Base | 33.5 | |
| 3 | DeepSeek-V4-Flash-Base | 31.2 | |
| 4 | GLM-4.5-Base | 30 |
Interactive version: theaggregate.ai/benchmark?slug=simpleqa · How It Works · Data refreshed daily, snapshot 2026-10-20.