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

Compositional Reasoning on VALSE

89.2Average Score

BEiTScore

41.349653.772366.19578.6177Jun 15, 2023Dec 10, 2023Jun 5, 2024Dec 1, 2024May 28, 2025Nov 22, 2025May 20, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.05
89.296.282.5-86.786.793.9--99.283.285.788.8
2026.05
87.787.186.4-90.587.787.7--91.28885.885.9
2026.05
87.19775.2-83.68390.3--9883.58390.1
2026.05
85.69578.1-82.285.382.3--96.88083.187.9
2026.05
85.28485.2-91.890.190.1--91.782.280.482.4
2026.05
82.394.175.1-8381.690.4--97.56673.979.4
2026.05
78.588.767.3-71.872.185.8--94.772.773.480.1
2023.06
76.784.579.267.876.483.489.456.757.894.7---
2023.06
76.7------------
2026.05
75.795.672.4-67.765.958.9--86.977.376.780.2
2026.05
73.874.373.7-78.16772--78.369.274.773.8
2023.06
72.578.677.764.474.481.288.654.754.893.7---
2023.06
72.5------------
2023.06
71.8------------
2023.06
71.676.871.76572.981.684.758.653.891.9---
2026.05
71.451.575.7-8673.594.4--84.963.155.755.9
2023.06
70.883.572.872.168.771.869.15146.893.8---
2023.06
70.477.474.668.87486.765.25044.296---
2023.06
7086.373.268.171.577.261.153.848.293.8---
2026.05
69.774.969.7-7766.266.3--73.869.568.970.1
2023.06
69.58375.667.570.273.868.646.449.694.8---
2026.05
69.572.369.8-78.163.464.3--77.869.568.666.9
2026.05
69.169.166.6-63.282.473.8--91.961.768.869.1
2026.05
69.171.769.1-75.763.665.1--69.969.567.767.3
2026.05
68.642.872.4-68.68972--96.960.254.858.1
2023.06
68.465.572.567.468.483.258.852.65195.8---
2026.05
66.655.663.7-60.969.880--89.279.752.547.7
2026.05
6673.966.3-63.485.262.6--92.558.26266
2023.06
65.569.358.36166.478.17253.251.688.8---
2023.06
65.455.571.56662.483.651.648.651.995.9---
2023.06
65.368.757.16165.477.871.854.15189.8---
2023.06
65.3------------
2026.05
64.274.663.1-60.682.359.8--8956.464.266.4
2024.11
58.59------------
2024.11
58.12------------
2024.11
57.57------------
2024.11
55.69------------
2023.06
50505050505050505050---
2024.11
48.53------------
2024.11
48.36------------
2024.11
48.06------------
2024.11
47.91------------
2024.11
43.65------------
2024.11
43.19------------