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

Commonsense Question Answering Suite on Commonsense QA

77.4BoolQ Accuracy

Full Precision

36.21646.90857.668.292Apr 5, 2026Apr 9, 2026Apr 14, 2026Apr 19, 2026Apr 24, 2026Apr 29, 2026May 4, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.04
77.478.877.269.275.245.958.668.9-
2026.05
71.883.789.182.683.768.282.479.776
2026.05
71.28189.681.181.866.581.478.576.3
2026.05
70.782.99383.385.471.779.680.980.6
2026.05
69.879.983.682.679.864.78177.679.5
2026.05
69.281.782.182.578.364.379.776.977.6
2026.05
68.980.281.682.179.663.279.176.576.9
2026.05
66.879.887.878.576.961.575.475.577.4
2026.05
6670.775.37878.758.972.671.572
2026.05
65.269.468.374.575.653.270.46867.4
2026.05
64.461.850.559.34730.84052.364.3
2026.04
63.771.94259.965.529.426.651.3-
2026.05
62.664.461.16056.94356.658.966.6
2026.04
62.353.827.749.3282530.239.5-
2026.05
62.264.353.159.144.232.940.751.756.8
2026.04
6268.937.555.659.326.220.647.2-
2026.04
61.860.634.852.436.224.433.243.3-
2026.04
61.568.437.655.55926.222.447.2-
2026.04
59.969.337.15557.826.320.846.6-
2026.04
59.862.832.851.54822.420.442.5-
2026.04
58.972.342.860.8653026.650.9-
2026.04
58.2653352.150.223.52243.4-
2026.04
57.566.535.453.75425.22144.8-
2026.04
5467.93553.955.424.72044.4-
2026.04
53.762.532.149.843.921.51940.4-
2026.04
52.865.932.951.252.523.61942.6-
2026.04
52.668.334.75454.225.42244.5-
2026.04
43.951.126.350.826.628.52936.6-
2026.04
37.849.62549.625.722.92733.9-