Noometry

Knowledge benchmark

SimpleQA Verified leaderboard

As of October 2026, GPT-6 Astra has the highest published SimpleQA Verified score on Noometry at 75.6%, out of 77 models with results.

Last verified

About SimpleQA Verified

Short fact-seeking questions with a single verifiable answer. It measures factual accuracy without web access.

Category
Knowledge
Introduced
2025
Size
1,000 questions
Format
Short answer
Unit
Percent (random guessing ≈ 0%)
Official site
epoch.ai

Top 15 models

  1. GPT-6 Astra 75.6%
  2. GPT-6.1 Sol 73.9%
  3. Gemini 3.1 Pro Preview 73.5%
  4. Claude Opus 5.5 72.2%
  5. Claude Fable 5.1 70.8%
  6. Claude Fable 5 70.7%
  7. Gemini 3.8 Flash 69.7%
  8. GPT-5.6 Sol 69.7%
  9. Gemini 3.7 Flash 69.2%
  10. Gemini 3 Flash Preview 66.8%
  11. Gemini 3.5 Flash 66.2%
  12. Gemini 3.6 Flash 66.2%
  13. GPT-5.5 63%
  14. GPT-6 Sol 60.7%
  15. Muse Spark 1.2 60.3%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1GPT-6 Astra OpenAI75.6%maxEpoch AI2026-08-30
2GPT-6.1 Sol OpenAI73.9%maxEpoch AI2026-09-29
3Gemini 3.1 Pro Preview Google73.5%highEpoch AI2026-08-10
4Claude Opus 5.5 Anthropic72.2%maxEpoch AI2026-09-22
5Claude Fable 5.1 Anthropic70.8%maxEpoch AI2026-09-01
6Claude Fable 5 Anthropic70.7%xhighEpoch AI2026-08-10
7Gemini 3.8 Flash Google69.7%highEpoch AI2026-09-02
8GPT-5.6 Sol OpenAI69.7%maxEpoch AI2026-08-10
9Gemini 3.7 Flash Google69.2%highEpoch AI2026-08-27
10Gemini 3 Flash Preview Google66.8%highEpoch AI2026-08-27
11Gemini 3.5 Flash Google66.2%highEpoch AI2026-08-27
12Gemini 3.6 Flash Google66.2%highEpoch AI2026-08-27
13GPT-5.5 OpenAI63%xhighEpoch AI2026-08-27
14GPT-6 Sol OpenAI60.7%maxEpoch AI2026-09-22
15Muse Spark 1.2 Meta60.3%xhighEpoch AI2026-08-27
16Claude Opus 5 Anthropic59.9%maxEpoch AI2026-08-10
17Muse Spark 1.1 Meta57.8%Epoch AI2026-08-31
18Grok 4.7 xAI56%xhighEpoch AI2026-09-22
19Qwen3.7 Max Alibaba (Qwen)55.8%Epoch AI2026-08-27
20Claude Opus 4.8 Anthropic53%maxEpoch AI2026-08-27
21DeepSeek V4 Pro DeepSeek52.9%maxEpoch AI2026-08-27
22Qwen3.6 Max Preview Alibaba (Qwen)52%Epoch AI2026-08-27
23Claude Opus 4.7 Anthropic51.7%xhighEpoch AI2026-08-27
24Kimi K3 Moonshot AI50.6%maxEpoch AI2026-08-27
25GPT-5 OpenAI50.1%highEpoch AI2026-08-27
26o3 OpenAI49.4%highEpoch AI2026-08-27
27Grok 4.6 xAI49.3%highEpoch AI2026-08-27
28Qwen3 Max Alibaba (Qwen)48.7%Epoch AI2026-08-27
29Grok 4.5 xAI48.3%highEpoch AI2026-08-27
30GPT-5.1 OpenAI48%highEpoch AI2026-08-27
31Qwen3.8 Max Alibaba (Qwen)47.3%xhighEpoch AI2026-09-02
32Claude Opus 4.6 Anthropic47%maxEpoch AI2026-08-27
33Claude Sonnet 5.5 Anthropic46.5%maxEpoch AI2026-09-29
34GPT-5.4 Pro OpenAI46.3%xhighEpoch AI2026-08-27
35Claude Opus 4.5 Anthropic45.7%32KEpoch AI2026-08-27
36GPT-5.4 OpenAI45.1%xhighEpoch AI2026-08-27
37Qwen3.6 Plus Alibaba (Qwen)44.1%Epoch AI2026-08-27
38GPT-5.6 Terra OpenAI43.2%maxEpoch AI2026-08-10
39GPT-6 Luna OpenAI41.4%maxEpoch AI2026-09-22
40o1 OpenAI41.1%highEpoch AI2026-08-31
41GLM-5.3 Z.ai (Zhipu)41%maxEpoch AI2026-08-28
42GPT-5.6 Luna OpenAI41%maxEpoch AI2026-08-10
43Qwen3 235B-A22B Alibaba (Qwen)40.4%Epoch AI2026-08-27
44Inkling Thinking Machines Lab40.3%xhighEpoch AI2026-08-27
45GPT-5.2 OpenAI37.1%xhighEpoch AI2026-08-27
46Kimi K2.7 Code Moonshot AI36.5%Epoch AI2026-08-27
47Claude Sonnet 4.6 Anthropic35.5%highEpoch AI2026-08-10
48Kimi K2.6 Moonshot AI34.9%Epoch AI2026-08-10
49Kimi K2.5 Moonshot AI34.3%Epoch AI2026-08-27
50GLM-5.2 Z.ai (Zhipu)34.2%maxEpoch AI2026-08-27
51GLM-5.1 Z.ai (Zhipu)34%Epoch AI2026-08-27
52Claude Sonnet 5 Anthropic33.7%maxEpoch AI2026-08-27
53DeepSeek V4 Flash DeepSeek33.6%maxEpoch AI2026-08-27
54Grok 4.3 xAI33.2%highEpoch AI2026-08-27
55GLM-4.7 Z.ai (Zhipu)32.2%Epoch AI2026-08-27
56GPT-4.1 OpenAI31.1%Epoch AI2026-08-31
57Claude Sonnet 4.5 Anthropic30.7%59KEpoch AI2026-08-27
58Grok 4.20 (Non-Reasoning) xAI30.2%Epoch AI2026-08-27
59GPT-5.4 mini OpenAI29.4%highEpoch AI2026-08-27
60GPT-4o OpenAI26%Epoch AI2026-08-31
61Qwen3.5 Plus Alibaba (Qwen)25.4%Epoch AI2026-08-27
62Claude Haiku 5.5 Anthropic23.8%maxEpoch AI2026-10-09
63GPT-5 Mini OpenAI21.6%highEpoch AI2026-08-10
64Qwen3.5-Flash Alibaba (Qwen)20.3%Epoch AI2026-08-27
65Mistral Large 4 Mistral AI20%highEpoch AI2026-10-09
66o4-mini OpenAI19.6%lowEpoch AI2026-08-27
67Inkling-Small Thinking Machines Lab19.1%xhighEpoch AI2026-08-27
68Qwen3.6 Flash Alibaba (Qwen)15.9%Epoch AI2026-08-27
69o3-mini OpenAI15.3%highEpoch AI2026-08-31
70Claude Haiku 4.5 Anthropic13.2%Epoch AI2026-08-10
71GPT-4.1 mini OpenAI12.7%Epoch AI2026-08-31
72Claude 3 Opus Anthropic12.6%Epoch AI2026-08-31
73GPT-5.4 nano OpenAI11.7%highEpoch AI2026-08-27
74GPT-5 Nano OpenAI11.7%highEpoch AI2026-08-10
75Gemma 4 31B IT Google10.4%Epoch AI2026-08-27
76GPT-4o mini OpenAI8.3%Epoch AI2026-08-31
77GPT-4.1 nano OpenAI6%Epoch AI2026-08-31

Compare the leaders

Other knowledge benchmarks

Frequently asked questions

What does SimpleQA Verified measure?

Short fact-seeking questions with a single verifiable answer. It measures factual accuracy without web access.

Which model has the highest SimpleQA Verified score?

As of October 2026, GPT-6 Astra has the highest published SimpleQA Verified score on Noometry at 75.6%, out of 77 models with results.

What is the best open-weight model on SimpleQA Verified?

DeepSeek V4 Pro has the highest SimpleQA Verified accuracy among open-weight models at 52.9%, ranking 21 of 77 overall.