Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Embodied Task Completion on ALFRED seen (test)

53.23Success Rate (SR)

Prompter

2.0115.307528.60541.9025Jun 2, 2023Nov 30, 2023May 29, 2024Nov 27, 2024May 27, 2025Nov 24, 2025May 25, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2023.06
53.2364.4325.8130.72
2026.05
52.0561.2124.626.69
2026.05
51.1760.2225.1230.21
2026.05
49.2357.8123.3725.23
2026.05
47.9556.9823.2928.42
2026.05
47.6157.3222.8226.31
2026.05
44.5551.133.884.92
2026.05
43.6453.1419.7624.32
2023.06
40.0548.6621.2828.97
2026.05
40.0548.6621.2828.97
2023.06
39.9644.142.563.47
2023.06
38.4245.4427.7834.93
2024.03
38.4245.44--
2026.05
33.0141.7116.6524.49
2023.06
28.8339.5511.2715.59
2024.03
28.8339.55--
2026.05
28.8339.5511.2715.59
2024.03
26.5237.09--
2026.05
25.7736.1510.3914.17
2023.06
25.1135.1510.3914.17
2024.03
25.1135.79--
2026.05
25.1135.796.6911.53
2024.03
18.226.77--
2024.03
15.3324.57--
2024.03
13.6321.11--
2023.06
3.989.422.026.27