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

Reward Modeling Evaluation on RM-Bench

85.3Chat Score

Flexible Principles ScalarRM

42.76453.80764.8575.893Apr 14, 2025Jun 20, 2025Aug 26, 2025Nov 1, 2025Jan 7, 2026Mar 15, 2026May 22, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2025.09
85.381.970.496.985.584.980.583.6
2025.09
80.4927795.588.986.483.486.2
2025.09
76.790.375.290.285.682.281.583.1
2025.09
76.592.478.791.991.486.277.184.9
2026.04
75.68066.594.28680.870.779.2
2025.09
75.484.569.390.492.184.163.579.9
2026.04
75.375.660.993.382.977.768.576.4
2026.05
75.2781.3964.8193.6785.6981.0169.6578.79
2026.05
75.176.6860.1885.4681.1775.2366.6774.36
2025.09
74.291.874.195.489.585.476.783.9
2025.04
73.962.453.995.889.475.849.371.5
2025.09
73.791.47590.691.285.771.282.7
2025.09
73.682.766.191.489.28264.278.5
2026.03
72.96254.693.678.3736170.8
2026.03
72.562.5569583.974.156.571.5
2026.03
72.261.653.494.783.973.753.770.5
2026.03
71.359.356.589.681.371.854.469.2
2026.04
71.361.953.289.684.672.250.269
2026.04
71.259.859.487.58171.456.169.5
2026.04
71.261.854.193.18473.25370
2026.03
7159.658.390.885.573.35169.9
2025.09
70.764.357.490.392.576.443.170.7
2026.05
70.6372.1957.2192.2881.4473.9963.7573.06
2026.03
69.860.654.596.588.974.947.370.3
2026.04
69.560.654.595.78974.746.670.1
2025.04
68.961.953.195.988.573.847.670
2025.04
68.76252.895.988.473.747.569.9
2026.04
68.451.152.376.553.66369.662.1
2026.03
67.760.460.883.486.473.644.268.1
2026.03
67.463.25295.687.873.447.569.5
2026.05
67.2669.4155.2692.1880.9671.8760.2671.03
2026.04
67.254.951.665.269.163.546.659.7
2026.03
67.165.159.991.187.175.150.170.8
2026.04
66.966.854.492.979.571.359.570.1
2026.03
66.8655791.690.775.843.870.1
2026.04
66.449.954.26979.56337.259.9
2026.04
66.451.451.885.486.966.737.763.8
2025.04
66.262.65889.384.973.948.369
2026.03
65.562.952.895.281.171.254.969.1
2026.04
64.952.350.562.382.860.229.557.5
2026.03
64.860.257.783.591.973.833.966.5
2025.04
64.563.3569087.572.645.468.5
2025.04
63.66256.989.182.271.849.667.9
2025.04
63.662.458.389.582.972.749.868.4
2025.04
63.25752.488.389.569.836.365.2
2025.04
63.163.453.690.485.471.645.867.6
2026.04
63.166.856.786.582.671.650.768.3
2026.04
62.762.557.89083.572.748.668.2
2025.04
62.563.254.690.486.571.644.967.7
2026.04
61.771.449.785.585.470.745.167.1
2025.04
61.457.45388.986.768.84065.2
2025.04
60.856.652.688.788.368.237.564.7
2025.04
60.260.553.889.692.171.134.866
2025.04
6061.353.889.990.77137.166.3
2026.04
59.960.256.986.587.270.240.265.9
2026.04
58.855.651.373.969.561.149.159.9
2025.04
58.561.554.189.191.370.835.365.8
2026.04
58.251.455.587.172.865.650.763
2026.03
58.149.747.751.820.354.280.951.8
2026.03
5850.35050.120.85481.552.1
2026.04
57.45752.787.288.667.134.963.5
2026.04
56.55851.786.887.167.335.363.2
2026.04
56.45349.351.248.354.954.352.5
2026.04
56.352.452.673.886.764.325.458.8
2026.03
55.851.546.284.765.160.952.659.5
2026.05
55.0461.7353.6563.2473.7558.3643.1458.42
2026.03
52.550.149.144.353.948.644.449
2026.03
47.949.447.24646.846.449.647.6
2026.03
44.449.447.855.343.148.755.749.2