Fact-seeking Question Answering on SimpleQA no web
55Accuracy
gpt-5-thinking
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 55 | 40 | |
2025.12 | 54 | 46 | |
2025.12 | 46 | 47 | |
2025.12 | 44 | 52 | |
2025.12 | 24 | 75 | |
2025.12 | 22 | 26 | |
2025.12 | 11 | 31 |
gpt-5-thinking
| Method | Links | ||
|---|---|---|---|
2025.12 | 55 | 40 | |
2025.12 | 54 | 46 | |
2025.12 | 46 | 47 | |
2025.12 | 44 | 52 | |
2025.12 | 24 | 75 | |
2025.12 | 22 | 26 | |
2025.12 | 11 | 31 |