Open-ended Question Answering on SimpleQA
60.9AccuracyGemini
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GeminiProvider=Gemini, Sample Size (N)=42882026.05 | 60.9 | 0.3769 | 0.1808 | 0.1724 | |
| AnthropicProvider=Anthropic, Sample Size (N)=42902026.05 | 48.2 | 0.203 | 0.3525 | 0.3451 | |
| OpenAIProvider=OpenAI, Sample Size (N)=43152026.05 | 33.6 | 0.5151 | 0.1982 | 0.1786 | |
| MistralProvider=Mistral, Sample Size (N)=43242026.05 | 26 | 0.602 | 0.5218 | 0.5117 | |
| xAIProvider=xAI, Sample Size (N)=41692026.05 | 22.9 | 0.6062 | 0.3646 | 0.3485 |