AutoGPT/classic/benchmark/reports/mini-agi/7_TestRevenueRetrieval_1.2....

31 lines
893 B
JSON

{
"command": "agbenchmark start --test TestRetrieval2.2",
"completion_time": "2023-07-17-14:04",
"metrics": {
"run_time": "28.08 seconds",
"highest_difficulty": "No successful tests"
},
"tests": {
"TestRetrieval2.2": {
"data_path": "agbenchmark/challenges/retrieval/r2.2_formatting",
"is_regression": false,
"reached_cutoff": false,
"answer": "It was $81.462 billion in 2022. In millions the answer is 81,462.",
"description": "Advanced version of the r2.1 challenge that also asks for specific formatting.",
"metrics": {
"difficulty": "intermediate",
"success": false,
"fail_reason": "assert 1 in [0.0]",
"success_%": 0.0,
"run_time": "27.857 seconds"
}
}
},
"config": {
"workspace": "${os.path.join(Path.home(), 'miniagi')}"
},
"additional": {
"model": "gpt-4"
}
}