Benchmark
SimpleQA
Factuality benchmarks measure how often models get facts right. Scores are percentages. Higher is better.
- Models and systems measured
- 38
- Scores recorded
- 40
- Sources
- 2
- IQ weight
- 0.96
Score distribution
- 37.9%
- Mean
- 28.9%
- Median
- 27.2%
- Std dev
- 6.3%
- 10th percentile
- 75%
- 90th percentile
- 1.8%
- Min
This benchmark has a weight of 0.96 for chat models, measured over 37 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | DeepSeek V3.2 Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 97.1% |
| 2 | Grok 4 Fast· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 95% |
| 3 | DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 93.4% |
| 4 | DeepSeek R1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 92.3% |
| 5 | ERNIE 5.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75% |
| 6 | Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.1% |
| 7 | Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.7% |
| 8 | GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.5% |
| 9 | Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 55.4% |
| 10 | Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.3% |
| 11 | Gemini 2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54% |
| 12 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 51.9% |
| 13 | Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 49.6% |
| 14 | o1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 47% |
| 15 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 44.4% |
| 16 | Gemini 3.1 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.3% |
| 17 | O1 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42.4% |
| 18 | GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38.2% |
| 19 | Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31% |
| 20 | DeepSeek V4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 28.9% |
| 21 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 27% |
| 22 | Gemini 2.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 26.9% |
| 23 | DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 24.9% |
| 24 | Trinity Large PreviewTrinity technical report · Table 4 · exact reported precision· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 23.9% |
| 25 | qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 23.9% |
| 26 | Mistral Largelatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 23.8% |
| 27 | Gemini 2.0 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 21.7% |
| 28 | MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 18.5% |
| 29 | MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 17.9% |
| 30 | o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 15% |
| 31 | Mistral Small 3.2 24B Instruct2506· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 12.1% |
| 32 | Gemini 2.5 Flash-Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 10.7% |
| 33 | Mistral Small 3.1 24b Instruct 2503· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 10.4% |
| 34 | Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 10% |
| 35 | Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 6.3% |
| 36 | Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 4% |
| 37 | Phi 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 3% |
| 38 | Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 2.2% |
| 39 | ERNIE 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 1.8% |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| MiMo V2 Flash Baseofficial Base table · 5-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 20.6% |
Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.