| [ | |
| { | |
| "agent_name": "A3-Qwen3.5-9B", | |
| "study_id": "2026-03-20_23-46-04_genericagent-checkpoints-qwen-qwen3-5-9b-web-pro-low-8903051-checkpoint-latest-on-visualwebarena-test-test", | |
| "date_time": "2026-03-20 23:46:04", | |
| "benchmark": "VisualWebArena", | |
| "score": 33.7, | |
| "std_err": 1.6, | |
| "benchmark_specific": "Yes", | |
| "benchmark_tuned": "No", | |
| "followed_evaluation_protocol": "Yes", | |
| "reproducible": "Yes", | |
| "comments": "Combined visualwebarena-train (461 tasks) and visualwebarena-test (449 tasks) for a total of 910 tasks. Model fine-tuned on WebSynth trajectories.", | |
| "original_or_reproduced": "Original" | |
| } | |
| ] | |