[ | |
{ | |
"agent_name": "GenericAgent-Claude-3.5-Sonnet", | |
"study_id": "2024-10-23_17-10-46", | |
"date_time": "2021-01-01 12:00:00", | |
"benchmark": "WorkArena-L2", | |
"score": 39.1, | |
"std_err": 3.2, | |
"benchmark_specific": "No", | |
"benchmark_tuned": "No", | |
"followed_evaluation_protocol": "Yes", | |
"reproducible": "Yes", | |
"comments": "NA", | |
"original_or_reproduced": "Original" | |
} | |
] |