[ | |
{ | |
"agent_name": "OrbyAgent-Claude-3.5-Sonnet", | |
"study_id": "orby-agent-v0-claude-3.5-webarena", | |
"benchmark": "WebArena", | |
"score": 36.5, | |
"std_err": 0, | |
"benchmark_specific": "No", | |
"benchmark_tuned": "No", | |
"followed_evaluation_protocol": "Yes", | |
"reproducible": "Yes", | |
"comments": "Use original WebArena eval protocol and task definitions", | |
"original_or_reproduced": "Original", | |
"date_time": "2025-02-21 15:00:22" | |
} | |
] |