An OpenAI factual question-answering benchmark that measures short-form factual accuracy and helps reveal hallucinations.
Browse the latest scores, model modes, release dates, and parameter sizes for SimpleQA.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 DeepSeek V3.2-Exp Thinking EnabledTools | 97.10 | 2025-09-29 | 671B | Free Commercial | |
DeepSeek-V3.1 Terminus Standard Mode | 96.80 | 2025-09-22 | 671B | Free Commercial | |
 Grok 4 Fast Thinking EnabledTools | 95.00 | 2025-09-19 | Unknown | Closed | |
4 | DeepSeek-V3.1 Thinking Enabled | 93.40 | 2025-08-20 | 671B | Free Commercial |
5 |  ERNIE 5.0 Thinking Enabled | 74.01 | 2025-11-13 | 2400B | Closed |
6 |  Gemini 3.0 Pro (Preview 11-2025) Thinking Enabled | 72.10 | 2025-11-18 | Unknown | Closed |
7 |  Claude Opus 4.6 Extended Thinking | 72.00 | 2026-02-05 | Unknown | Closed |
8 | Gemini 3.0 Flash Thinking Enabled | 68.70 | 2025-12-17 | Unknown | Closed |
9 |  GPT-4.5 Standard Mode | 62.50 | 2025-02-28 | Unknown | Closed |
10 |  Qwen3-235B-A22B-2507 Standard Mode | 54.30 | 2025-07-21 | 235B | Free Commercial |
11 | Gemini-2.5-Pro-Preview-05-06 Standard Mode | 54.00 | 2025-05-06 | Unknown | Closed |
12 | Gemini 2.5-Pro Standard Mode | 54.00 | 2025-06-05 | Unknown | Closed |
13 | Gemini 2.5 Pro Experimental 03-25 Standard Mode | 52.90 | 2025-03-25 | Unknown | Closed |
14 | OpenAI o3 Standard Mode | 49.40 | 2025-04-16 | Unknown | Closed |
15 | ERNIE-4.5-300B-A47B Standard Mode | 45.90 | 2025-06-30 | 300B | Free Commercial |
16 |  Gemini 2.0 Pro Experimental Standard Mode | 44.30 | 2025-02-05 | Unknown | Closed |
17 | Inkling Thinking Enabled | 43.90 | 2026-07-15 | 975B | Free Commercial |
18 | Grok 3 Standard Mode | 43.40 | 2025-02-17 | Unknown | Closed |
19 | OpenAI o1 Standard Mode | 42.60 | 2024-12-05 | Unknown | Closed |
20 | GPT-4o(2025-03-27) Standard Mode | 40.30 | 2025-03-27 | Unknown | Closed |
21 | GPT-4o(2024-11-20) Standard Mode | 38.80 | 2024-11-20 | Unknown | Closed |
22 | GPT-4o Standard Mode | 38.20 | 2024-05-13 | Unknown | Closed |
23 |  Kimi K2 Standard Mode | 31.00 | 2025-07-11 | 1000B | Free Commercial |
24 | DeepSeek-R1 Standard Mode | 30.10 | 2025-01-20 | 671B | Free Commercial |
25 | Gemini 2.0 Flash Experimental Standard Mode | 29.90 | 2024-12-11 | Unknown | Closed |
26 | Claude 3.5 Sonnet New Standard Mode | 28.40 | 2024-10-22 | Unknown | Closed |
27 | DeepSeek-R1-0528 Thinking Enabled | 27.80 | 2025-05-28 | 671B | Free Commercial |
28 | DeepSeek-V3-0324 Standard Mode | 27.20 | 2025-03-24 | 671B | Free Commercial |
29 | Gemini 2.5 Flash Thinking Enabled | 26.90 | 2025-04-17 | Unknown | Closed |
30 | Gemini 2.5 Flash Standard Mode | 25.80 | 2025-04-17 | Unknown | Closed |
