Benchmark
SimpleQA Benchmark
What is SimpleQA?
SimpleQA is a factuality benchmark developed by OpenAI that measures the short-form factual accuracy of large language models. The benchmark contains 4,326…
- Released
- 2024-10-30
- Modality
- text
- Evaluates
- reasoning, factuality, general
- Openness
- restricted
- Importer
- LLM Stats
- Reported scores
- 47
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/simpleqa?top_n=500
SimpleQA paper, code and dataset
SimpleQA results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-R1-0528 | DeepSeek | 0.923 | 2025-05-28 | evidence |
| DeepSeek-V3 | DeepSeek | 0.249 | 2024-12-25 | evidence |
| DeepSeek-V3.1 | DeepSeek | 0.934 | 2025-01-10 | evidence |
| DeepSeek-V3.2-Exp | DeepSeek | 0.971 | 2025-09-29 | evidence |
| DeepSeek-V4-Flash-0423 | DeepSeek | 0.289 | 2026-04-23 | evidence |
| DeepSeek-V4-Flash-Max | DeepSeek | 0.341 | 2026-04-23 | evidence |
| DeepSeek-V4-Pro-Max | DeepSeek | 0.579 | 2026-04-23 | evidence |
| ERNIE 4.5 | Baidu | 0.018 | 2025-06-25 | evidence |
| ERNIE 5.0 | Baidu | 0.75 | 2026-01-22 | evidence |
| Gemini 2.0 Flash-Lite | 0.217 | 2025-02-05 | evidence | |
| Gemini 2.5 Flash | 0.269 | 2025-05-20 | evidence | |
| Gemini 2.5 Flash-Lite | 0.107 | 2025-06-17 | evidence | |
| Gemini 2.5 Pro | 0.508 | 2025-05-20 | evidence | |
| Gemini 2.5 Pro Preview 06-05 | 0.54 | 2025-06-05 | evidence | |
| Gemini 3 Flash | 0.687 | 2025-12-17 | evidence | |
| Gemini 3 Pro | 0.721 | 2025-11-18 | evidence | |
| Gemini 3.1 Flash-Lite | 0.433 | 2026-03-03 | evidence | |
| Gemma 3 12B | 0.063 | 2025-03-12 | evidence | |
| Gemma 3 1B | 0.022 | 2025-03-12 | evidence | |
| Gemma 3 27B | 0.1 | 2025-03-12 | evidence | |
| Gemma 3 4B | 0.04 | 2025-03-12 | evidence | |
| GPT-4.5 | OpenAI | 0.625 | 2025-02-27 | evidence |
| GPT-4o | OpenAI | 0.382 | 2024-08-06 | evidence |
| Grok 4 Fast | xAI | 0.95 | 2025-08-28 | evidence |
| Kimi K2 Base | Moonshot AI | 0.353 | 2025-07-11 | evidence |
| Kimi K2 Instruct | Moonshot AI | 0.31 | 2025-07-11 | evidence |
| Kimi K2-Instruct-0905 | Moonshot AI | 0.31 | 2025-09-05 | evidence |
| MiniMax M1 40K | MiniMax | 0.179 | 2025-06-16 | evidence |
| MiniMax M1 80K | MiniMax | 0.185 | 2025-06-16 | evidence |
| Mistral Large 3 (675B Base) | Mistral | 0.238 | 2025-12-04 | evidence |
| Mistral Large 3 (675B Instruct 2512 Eagle) | Mistral | 0.238 | 2025-12-04 | evidence |
| Mistral Large 3 (675B Instruct 2512 NVFP4) | Mistral | 0.238 | 2025-12-04 | evidence |
| Mistral Large 3 (675B Instruct 2512) | Mistral | 0.238 | 2025-12-04 | evidence |
| Mistral Small 3.1 24B Instruct | Mistral | 0.1043 | 2025-03-17 | evidence |
| Mistral Small 3.2 24B Instruct | Mistral | 0.121 | 2025-06-20 | evidence |
| o1 | OpenAI | 0.47 | 2024-12-17 | evidence |
| o1-preview | OpenAI | 0.424 | 2024-09-12 | evidence |
| o3-mini | OpenAI | 0.15 | 2025-01-30 | evidence |
| Phi 4 | Microsoft | 0.03 | 2024-12-12 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.519 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.444 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.27 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.239 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.554 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.48 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.496 | 2025-09-22 | evidence |
| Qwen3-235B-A22B-Instruct-2507 | Qwen | 0.543 | 2025-07-22 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.