Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
Evaluate an AI's ability to provide accurate and helpful travel advice for a specific, slightly unusual destination, including cultural nuances and practical tips.
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3 Haiku | Gemini Flash 1.5 | GPT 4o Mini | |
|---|---|---|---|---|
| Score | 3rd 50.3% | 2nd 54.0% | 1st 60.7% | |
| 60.7% | 63% | 56% | 63% | |
| 64.7% | 69% | 50% | 75% | |
| 39.7% | 19% | 56% | 44% |