57 lines
1.8 KiB
JSON
57 lines
1.8 KiB
JSON
[
|
|
{
|
|
"website":"https://www.anthropic.com/claude",
|
|
"prompt":"Does this website contain pricing information?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://mendable.ai/pricing",
|
|
"prompt":"Does this website contain pricing information?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://openai.com/news",
|
|
"prompt":"Does this website contain a list of research news?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://agentops.ai",
|
|
"prompt":"Does this website contain a code snippets?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://ycombinator.com/companies",
|
|
"prompt":"Does this website contain a list bigger than 5 of ycombinator companies?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://firecrawl.dev",
|
|
"prompt":"Does this website contain a list bigger than 5 of ycombinator companies?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://en.wikipedia.org/wiki/T._N._Seshan",
|
|
"prompt":"Does this website talk about Seshan's career?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://mendable.ai/blog",
|
|
"prompt":"Does this website contain multiple blog articles?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://mendable.ai/blog",
|
|
"prompt":"Does this website contain multiple blog articles?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://news.ycombinator.com/",
|
|
"prompt":"Does this website contain a list of articles in a table markdown format?",
|
|
"expected_output":"yes"
|
|
},
|
|
{
|
|
"website":"https://www.vellum.ai/llm-leaderboard",
|
|
"prompt":"Does this website contain a model comparison table?",
|
|
"expected_output":"yes"
|
|
}
|
|
] |