SimpleQA Verified
General QA · 2025-06-01
SimpleQA Verified contains 1,000 factoid questions covering politics, science and technology, art, sports, geography, music, and other topics. Scores report answer accuracy.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3.1 Pro Preview | 77.3 |
| GPT-5.6 Sol | 71.6 |
| Gemini 3.6 Flash | 68.7 |
| Gemini 3.5 Flash | 68.4 |
| Claude Fable 5 | 68.3 |
| Qwen3-Max (2025-09-23) | 67.5 |
| Muse Spark | 66.3 |
| GPT-5.5 Pro | 64.5 |
| GPT-5.5 | 63.1 |
| Qwen3.7-Max | 58.5 |
| DeepSeek-V4-Pro | 57.0 |
| Qwen3.6-Max-Preview | 56.9 |
| Claude Opus 5 | 56.7 |
| Grok 4.5 | 53.5 |
| o3 | 53.0 |
| Opus 4.7 | 50.6 |
| GPT-5 | 50.6 |
| Qwen3 235B A22B Thinking 2507 | 50.1 |
| Qwen3.6 Plus (2026-04-02) | 49.1 |
| Grok 4 | 47.9 |
| GPT-5.4 Pro | 47.8 |
| Opus 4.6 | 46.5 |
| GPT-5.4 | 44.8 |
| Gemini 3.5 Flash-Lite | 44.1 |
| Inkling | 43.9 |
| Gemini 3.1 Flash-Lite Preview | 43.3 |
| GPT-5.6 Terra | 43.1 |
| Kimi K3 | 42.7 |
| Opus 4.5 | 41.8 |
| GPT-5.6 Luna | 41.7 |
| Opus 4.8 | 39.5 |
| Kimi K2.7 Code | 39.2 |
| Kimi K2.6 | 38.7 |
| GPT-5.2 | 38.2 |
| GLM-5.2 | 38.1 |
| Grok 4.3 | 38.0 |
| GLM-5.1 | 37.3 |
| Grok 4.20 | 35.1 |
| Opus 4.1 | 34.8 |
| DeepSeek-V4-Flash | 34.1 |