[ | |
{ | |
"agent_name": "GenericAgent-Claude-3.5-Sonnet", | |
"study_id": "b5fc5be7-54cc-4fc1-a9ee-73447b9c3eae", | |
"benchmark": "WebArena", | |
"score": 36.2, | |
"std_err": 1.7, | |
"benchmark_specific": "No", | |
"benchmark_tuned": "No", | |
"followed_evaluation_protocol": "Yes", | |
"reproducible": "Yes", | |
"comments": "NA", | |
"original_or_reproduced": "Original", | |
"date_time": "2024-11-29 22:37:46" | |
} | |
] |