SimpleQA Verified

Short factual questions with one correct answer, scored for accuracy without web search. Run by Epoch AI.

CategoryKnowledge
MetricAccuracy
SourceEpoch AI (evaluator)
LicenseCC BY 4.0
Benchmark pageepoch.ai
StatusScored
Weight1.0 within Knowledge
FitDiscrimination 0.67, noise 0.22

Results

#ModelProviderResultDate
1 Claude Fable 5.2 Max Anthropic 94.0% 2026-11-06
2 Gemini 4 Carbon High Google 77.7% 2026-11-02
3 Gemini 4 Argon High Google 76.0% 2026-10-13
4 GPT-6 Astra Max OpenAI 75.6% 2026-08-30
5 GPT-6.1 Sol Max OpenAI 73.9% 2026-09-29
6 Gemini 3.1 Pro Preview High Google 73.5% 2026-08-10
7 Claude Opus 5.5 Max Anthropic 72.2% 2026-09-22
8 Claude Fable 5.1 Max Anthropic 70.8% 2026-09-01
9 Claude Fable 5 Extra High Anthropic 70.7% 2026-08-10
10 Gemini 3.8 Flash High Google 69.7% 2026-09-02
11 GPT-5.6 Sol Max OpenAI 69.7% 2026-08-10
12 Gemini 3.7 Flash High Google 69.2% 2026-08-27
13 Gemini 3 Flash Preview High Google 66.8% 2026-08-27
14 Gemini 3.6 Flash High Google 66.2% 2026-08-27
15 Gemini 3.5 Flash High Google 66.2% 2026-08-27
16 GPT-5.5 Extra High OpenAI 63.0% 2026-08-27
17 Kimi K3.1 Pro Max Moonshot AI 62.2% 2026-11-06
18 GPT-6 Sol Max OpenAI 60.7% 2026-09-22
19 Muse Spark 1.2 Extra High Meta 60.3% 2026-08-27
20 Claude Opus 5 Max Anthropic 59.9% 2026-08-10
21 Muse Spark 1.1 Meta 57.8% 2026-08-31
22 GPT-6.1 Terra Max OpenAI 57.3% 2026-10-26
23 Muse Spark Open Extra High Meta 56.6% 2026-10-15
24 Grok 4.7 Extra High xAI 56.0% 2026-09-22
25 Qwen3.7 Max Alibaba 55.8% 2026-08-27
26 Claude Opus 4.8 Max Anthropic 53.0% 2026-08-27
27 DeepSeek V4 Pro 0813 Max DeepSeek 52.9% 2026-08-27
28 Qwen3.6 Max Preview Alibaba 52.0% 2026-08-27
29 Claude Opus 4.7 Extra High Anthropic 51.7% 2026-08-27
30 Kimi K3 Max Moonshot AI 50.6% 2026-08-27
31 GPT-5 High OpenAI 50.1% 2026-08-27
32 o3 High OpenAI 49.4% 2026-08-27
33 Grok 4.6 High xAI 49.3% 2026-08-27
34 Grok 4.6 Extra High xAI 48.9% 2026-08-27
35 Qwen3 Max Alibaba 48.8% 2026-08-27
36 Grok 4.5 High xAI 48.3% 2026-08-27
37 GPT-5.1 High OpenAI 48.0% 2026-08-27
38 Qwen3.8 Max 0902 Extra High Alibaba 47.3% 2026-09-02
39 Claude Opus 4.6 Max Anthropic 47.0% 2026-08-27
40 DeepSeek V4 Pro Max DeepSeek 47.0% 2026-08-27
41 Claude Sonnet 5.5 Max Anthropic 46.5% 2026-09-29
42 GPT-5.4 Pro Extra High OpenAI 46.3% 2026-08-27
43 Qwen3.8 Max Extra High Alibaba 45.8% 2026-08-27
44 Claude Opus 4.5 Thinking Anthropic 45.7% 2026-08-27
45 GPT-5.4 Extra High OpenAI 45.1% 2026-08-27
46 Doubao Seed 2.1 Pro High ByteDance 44.7% 2026-10-28
47 Qwen3.6 Plus Alibaba 44.1% 2026-08-27
48 GPT-5.6 Terra Max OpenAI 43.2% 2026-08-10
49 DeepSeek V4.1 Flash Max DeepSeek 42.9% 2026-10-13
50 DeepSeek V4.1 Flash 1017 Max DeepSeek 42.5% 2026-10-19
51 Doubao Seed Evolving (Nov 2026) High ByteDance 41.9% 2026-11-02
52 GPT-6 Luna Max OpenAI 41.4% 2026-09-22
53 o1 High OpenAI 41.1% 2026-08-31
54 GLM-5.3 Max Zhipu AI 41.0% 2026-08-28
55 GPT-5.6 Luna Max OpenAI 41.0% 2026-08-10
56 Qwen3 235B-A22B Thinking 2507 Alibaba 40.4% 2026-08-27
57 Inkling Extra High Thinking Machines 40.3% 2026-08-27
58 Doubao-Seed-2.0 Pro High ByteDance 39.4% 2026-10-28
59 GPT-5.2 Extra High OpenAI 37.1% 2026-08-27
60 Kimi K2.7 Code Moonshot AI 36.5% 2026-08-27
61 Claude Sonnet 4.6 High Anthropic 35.5% 2026-08-10
62 Kimi K2.6 Moonshot AI 34.9% 2026-08-10
63 Kimi K2.5 Moonshot AI 34.3% 2026-08-27
64 GPT-5.2 High OpenAI 34.3% 2026-08-27
65 GLM-5.2 Max Zhipu AI 34.2% 2026-08-27
66 GLM-5.1 Zhipu AI 34.0% 2026-08-27
67 Claude Sonnet 5 Max Anthropic 33.7% 2026-08-27
68 DeepSeek V4 Flash 0731 Max DeepSeek 33.6% 2026-08-27
69 Grok 4.3 High xAI 33.2% 2026-08-27
70 Claude Sonnet 5 Extra High Anthropic 32.9% 2026-08-27
71 Claude Sonnet 4.6 Max Anthropic 32.8% 2026-08-27
72 GPT-5.2 Low OpenAI 32.8% 2026-08-27
73 GPT-5.2 Medium OpenAI 32.7% 2026-08-27
74 GLM-4.7 Zhipu AI 32.2% 2026-08-27
75 Doubao Seed 2.0 Lite (Apr 2026) High ByteDance 31.5% 2026-10-28
76 GPT-4.1 OpenAI 31.1% 2026-08-31
77 Claude Sonnet 4.5 Thinking Anthropic 30.7% 2026-08-27
78 Grok 4.20 (Reasoning) xAI 30.2% 2026-08-27
79 Doubao Seed 2.1 Turbo High ByteDance 29.7% 2026-10-30
80 GPT-5.4 mini High OpenAI 29.4% 2026-08-27
81 GPT-4o (2024-08-06) OpenAI 26.0% 2026-08-31
82 Qwen3.5 Plus Alibaba 25.4% 2026-08-27
83 Claude Haiku 5.5 Max Anthropic 23.8% 2026-10-09
84 Claude Sonnet 4.5 Anthropic 23.7% 2026-08-10
85 Mistral Large 4 High Mistral 22.4% 2026-11-02
86 GPT-5 Mini High OpenAI 21.6% 2026-08-10
87 Qwen3.5 Flash Alibaba 20.3% 2026-08-27
88 Mistral Large 4 Preview High Mistral 20.0% 2026-10-09
89 o4-mini Low OpenAI 19.6% 2026-08-27
90 Inkling Small Extra High Thinking Machines 19.1% 2026-08-27
91 o4-mini High OpenAI 18.8% 2026-08-27
92 Seed 1.6 ByteDance 17.4% 2026-10-30
93 Qwen3.6 Flash Alibaba 15.9% 2026-08-27
94 o3-mini High OpenAI 15.3% 2026-08-31
95 Claude Haiku 4.5 Anthropic 13.2% 2026-08-10
96 GPT-4.1 mini OpenAI 12.7% 2026-08-31
97 Claude 3 Opus Anthropic 12.6% 2026-08-31
98 Claude Haiku 4.5 Thinking Anthropic 12.6% 2026-08-27
99 GPT-5.4 nano High OpenAI 11.7% 2026-08-27
100 GPT-5 Nano High OpenAI 11.7% 2026-08-10
101 Gemma 4 31B IT Google 10.4% 2026-08-27
102 GPT-4o mini OpenAI 8.3% 2026-08-31
103 GPT-4.1 nano OpenAI 6.0% 2026-08-31