SimpleQA Verified: leaderboard
Factual accuracy benchmark testing short factoid questions with verifiable answers. Measures how often models give correct, non-hallucinated responses to straightforward knowledge queries.
Metric: Accuracy (%). Source: epoch.ai. Status: years away from saturation. 78 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 (Max) | 75.6 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 73.5 |
| 3 | Claude Fable 5.1 (Max) | 70.8 |
| 4 | GPT-5.6 Sol (Max) | 69.7 |
| 5 | Gemini 3.7 Flash (High) | 69.2 |
| 6 | Gemini 3 Flash (Preview) (High) | 66.8 |
| 7 | Gemini 3.5 Flash (High) | 66.2 |
| 8 | Gemini 3.6 Flash (High) | 66.2 |
| 9 | GPT-5.5 (xHigh) | 63 |
| 10 | Muse Spark 1.2 (xHigh) | 60.3 |
| 11 | Claude Opus 5 (Max) | 59.9 |
| 12 | Muse Spark 1.1 | 57.79 |
| 13 | Qwen 3.7 Max | 55.77 |
| 14 | Claude Opus 4.8 (Max) | 53 |
| 15 | DeepSeek V4 Pro (0813) (Max) | 52.91 |
Interactive version: theaggregate.ai/benchmark?slug=simpleqa-verified · How It Works · Data refreshed daily, snapshot 2026-09-05.