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

Interactive Decision Making on ALFWorld Seen (val)

100Pick Reward

SCPO

2.13627.54352.9578.357Jun 24, 2026Jun 25, 2026Jun 27, 2026Jun 29, 2026Jul 1, 2026Jul 3, 2026Jul 5, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.06
100-10097.292.989.394.395.3
2026.06
99.1-90.397.381.890.881.991.4
2026.06
97.7-82.798.883.789.379.290.8
2026.06
96-88.693.496.592.890.993.7
2026.06
94.4-67.594.894.479.876.486.7
2026.06
92.9-75.274.886.373.765.378.5
2026.06
92.8-63.362.16926.658.760.3
2026.07
92.860.36963.326.662.158.7-
2026.06
92.3-6492.589.580.368.880.4
2026.06
90.8-66.189.374.772.564.777.6
2026.06
88.6-7597.690.784.274.287
2026.06
88.3-52.87162.866.456.969.7
2026.07
88.369.762.852.866.47156.9-
2026.06
87.6-78.287.381.371.948.975.5
2026.06
85.5-33.578.976.274.769.173.7
2026.06
85.3-53.784.578.259.753.572.8
2026.07
79.390.110086.994.99884.6-
2026.07
78.387.897.283.686.589.299.1-
2026.06
75.3-60.831.256.721.649.848
2026.07
75.34856.760.821.631.249.8-
2026.07
73.985.599.685.683.188.884.9-
2026.07
68.575.883.479.180.280.560.1-
2026.06
64.8-40.557.160.646.447.454.4
2026.07
64.854.460.640.546.457.147.4-
2026.06
62-41.644.930.936.323.842.7
2026.06
48.5-35.434.313.218.217.631.2
2026.06
35.3-22.221.713.619.43.721.8
2026.07
35.321.813.622.219.421.73.7-
2026.06
33.4-21.619.36.92.83.214.8
2026.06
17.4-20.515.76.27.7212.8
2026.07
17.412.86.220.57.715.72-
2026.06
5.9-5.53.39.74.204.1
2026.07
5.94.19.75.54.23.30-
2026.04
-0.25------
2026.04
-0.7173------
2026.04
-0.7286------
2026.04
-0.5286------
2026.04
-0.4357------
2026.04
-0.2214------
2026.04
-0.5643------
2026.04
-0.5714------
2026.04
-0.4429------
2026.04
-0.4071------
2026.04
-0.5------
2026.04
-0.8286------
2026.04
-0.7687------
2026.04
-0.6643------
2026.04
-0.7643------
2026.04
-0.5429------
2026.04
-0.85------
2026.04
-0.8357------
2026.04
-0.8677------
2026.04
-0.8429------
2026.06
-------92.77
2026.06
-------95.44