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

Embodied Task on ALFWorld

96.9Overall Success Rate

GRPO w/ SG & GR

0.38825.44450.575.556Mar 1, 2026Mar 6, 2026Mar 12, 2026Mar 17, 2026Mar 23, 2026Mar 28, 2026Apr 3, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
96.91001001001008793.8-
2026.04
95.310010010010090.584-
2026.03
94.8-------
2026.03
93.598.585.19993.896.490.4-
2026.03
93.598.585.19993.896.490.4-
2026.04
92.210091.710089.510070.8-
2026.03
92.199.188.198.491.992.789.5-
2026.04
91.497.18096.210087.580-
2026.03
90.897.782.797.883.789.379.2-
2026.03
90.897.782.798.883.789.379.2-
2026.03
90.897.782.798.883.789.379.2-
2026.03
90.291.888.695.990.286.585.2-
2026.03
89.998.679.998.290.580.184.3-
2026.03
89.997.971.4909095.587.5-
2026.03
89.997.971.4909095.587.5-
2026.04
89.810085.894.681.985.780.1-
2026.04
89.810010078.110078.8100-
2026.04
87.995.680.410086.778.775.2-
2026.03
87.592.68096.294.79576.5-
2026.03
87.592.68096.294.79576.5-
2026.03
86.794.467.594.894.479.876.4-
2026.03
86.794.467.594.894.479.876.4-
2026.03
86.794.467.594.894.479.876.4-
2026.04
86.795.788.910092.367.786.4-
2026.03
86.19676.591.891.371.779.5-
2026.04
83.610072.710088.958.889.5-
2026.03
82.5-------
2026.04
81.394.110066.7766883.3-
2026.04
81.295.696.278.173.272.472-
2026.03
80.492.36492.589.580.368.8-
2026.04
79.992.685.770.686.679.365-
2026.04
78.291.981.87673.376.170-
2026.03
77.690.866.189.374.772.564.7-
2026.03
77.690.866.189.374.772.564.7-
2026.03
77.690.866.189.374.772.564.7-
2026.04
77.690.866.189.374.772.564.7-
2026.03
75.587.678.287.381.371.948.9-
2026.03
75.587.678.287.381.371.948.9-
2026.03
75.587.678.287.381.371.948.9-
2026.04
75.587.678.287.381.371.948.9-
2026.03
72.885.353.784.578.259.753.5-
2026.03
72.885.353.784.578.259.753.5-
2026.03
72.885.353.784.578.259.753.5-
2026.04
72.793.110083.352.654.560.7-
2026.03
69.788.352.87162.866.456.9-
2026.03
65.4-------
2026.03
62.589.536.3605064.926.3-
2026.03
62.589.536.3605064.926.3-
2026.04
62.589.536.3605064.926.3-
2026.03
60.392.863.362.16926.658.7-
2026.03
60.392.863.362.16926.658.7-
2026.04
60.392.863.362.16926.658.7-
2026.04
58.687.85029.258.327.380-
2026.04
55.587.95068.441.717.448.5-
2026.03
54.778.154.856.1316526.9-
2026.03
54.778.154.856.1316526.9-
2026.04
54.778.154.856.1316526.9-
2026.03
54.464.840.557.160.646.447.4-
2026.03
4875.360.831.256.721.649.8-
2026.03
4875.360.831.256.721.649.8-
2026.04
4875.360.831.256.721.649.8-
2026.04
47.174.346.251.9502833.3-
2026.03
46.321675552716-
2026.04
46.321675552716-
2026.04
4577.161.540.731.32433.3-
2026.04
44.177.324.547.941.724.622.5-
2026.04
43.864.933.346.413.333.333.3-
2026.03
42.76241.644.930.936.323.8-
2026.03
42.76241.644.930.936.323.8-
2026.04
42.76241.644.930.936.323.8-
2026.04
42.265.566.741.957.917.415-
2026.03
41.454.338.548.156.23216.7-
2026.04
41.454.338.548.156.23216.7-
2026.04
38.674.338.525.9253216.7-
2026.04
37.168.638.53725324.2-
2026.03
33.6545526.936.420.87.69-
2026.04
33.6545526.936.420.87.69-
2026.03
31.248.535.434.313.218.217.6-
2026.03
31.248.535.434.313.218.217.6-
2026.04
31.248.535.434.313.218.217.6-
2026.03
29.764.533.32012.533.33.84-
2026.04
29.764.533.32012.533.33.84-
2026.03
21.835.322.221.713.619.43.7-
2026.03
21.462.838.522.212.580-
2026.03
21.462.838.522.212.580-
2026.04
21.462.838.522.212.580-
2026.04
21.154.214.318.5012.119-
2026.04
20.342.416.708.39.128-
2026.04
16.422.915.414.818.8168.3-
2026.04
15.22724.34.520.510.20-
2026.03
14.833.421.619.36.92.83.2-
2026.04
14.833.421.619.36.92.83.2-
2026.04
12.928.623.17.46.380-
2026.03
12.817.420.515.76.27.72-
2026.04
10.224.212.500012.1-
2026.03
4.15.95.53.39.74.20-
2026.04
-------83.58
2026.04
-------83.58
2026.04
-------86.87
2026.04
-------91.2
Showing 100 of 108 rows