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

Commonsense Reasoning on BoolQ, PIQA, SIQA, HellaS., WinoG., ARC-e, ARC-c, OBQA (test)

88BoolQ Accuracy

PaLM (540B)

71.15275.52679.984.274Feb 14, 2024Jun 22, 2024Oct 30, 2024Mar 9, 2025Jul 16, 2025Nov 23, 2025Apr 2, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2024.05
8882.3-83.481.176.65353.4-
2025.07
78.1390.4882.1496.6288.2495.287.7191.288.72
2025.07
77.6191.5182.496.9390.379688.7492.889.55
2024.07
76.991.482.196.786.989.679.486.185.9
2024.05
75.886.981.294.48789.677.985.284.8
2025.07
75.7290.2181.4295.3189.1193.182.7688.286.98
2025.05
75.6388.8580.3595.6486.1191.1680.8986.485.63
2025.07
75.4489.7281.7895.5887.6992.8984.39087.17
2024.07
75.388.982.294.9868979.884.985.3
2026.04
75.2691.0582.5595.8190.2195.4485.6289.688.19
2026.04
75.1788.7477.5895.2189.1192.9384.738886.43
2024.06
75.186.476.775.483.390.479.18581.4
2024.06
7589.781.19583.391.280.585.885.2
2025.07
74.9589.3480.395.5285.6490.6679.5285.885.22
2024.06
74.886.779.993.985.190.279.384.284.2
2025.07
74.7789.1279.6395.8486.3591.0880.7285.285.34
2024.05
74.689.379.995.585.690.580.485.885.2
2024.02
74.689.379.995.585.690.580.485.885.2
2024.06
74.689.379.995.585.690.580.485.885.2
2024.06
74.689.7819585.890.581.586.885.6
2025.05
74.5688.5280.0995.1786.7490.1979.7884.684.96
2025.05
74.5388.5280.0495.4585.3289.7378.9284.284.59
2024.05
74.588.880.395.584.790.179.187.285
2024.02
74.588.880.395.584.790.179.187.285
2024.06
74.588.880.395.584.790.179.187.285
2025.05
74.4688.1481.3794.8185.0889.1880.728684.97
2025.03
74.489.1281.3795.5586.6692.9783.1988.886.51
2024.05
74.388.181.895.187.391.181.787.285.8
2025.07
73.9488.3680.2595.8585.9591.0480.5585.885.22
2024.07
73.888.280.49485.587.578.18483.9
2025.05
73.7687.1179.8494.7284.2989.9879.6184.684.24
2025.07
73.7388.7480.9695.6387.9290.4577.8286.685.23
2026.04
73.7384.681.2792.3386.8288.2477.2187.483.95
2026.03
73.687.48195.286.59079.88584.8
2026.04
73.684.480.291.584.584.772.181.281.53
2026.04
73.683.9580.587.128587.7976.888782.73
2026.04
73.4990.4479.1995.039093.7984.7388.6786.92
2026.04
73.4989.579.9994.689.993.1884.389.486.79
2024.07
73.483.482.188.384.986.666.782.581
2024.05
73.385.680.891.685.584.273.783.382.3
2024.08
73.386.48294.486.187.474.18783.8
2025.03
73.2788.2578.9294.9687.2190.9577.9986.284.72
2024.05
73.285.482.193.485.187.873.384.483.1
2024.08
73.285.582.494.586.386.874.68683.7
2026.03
73.284.581.990.885.584.671.582.981.8
2025.05
73.1885.3174.3686.5774.1990.9580.298481.11
2026.04
73.1583.6880.0974.5785.9587.3372.5386.280.43
2024.07
73.185.468.578.566.189.879.974.877
2024.05
73.185.468.578.566.189.879.974.877
2024.02
73.185.468.578.566.189.879.974.877
2024.08
73.185.468.578.566.189.879.974.877
2024.07
73.185.468.578.566.189.879.974.877
2024.07
73.185.468.578.566.189.879.974.877
2026.03
73.185.468.578.566.189.879.974.877
2026.04
73.185.468.578.566.189.879.974.877.01
2025.05
73.0985.9675.0890.4875.5390.7481.484.482.09
2024.05
72.98379.892.48386.67280.181.2
2024.11
72.985.680.79283.785.671.685.682.2
2024.07
72.985.677.892.783.389.777.682.882.8
2026.03
72.982.281.487.98482.769.181.180.2
2026.03
72.98282.889.585.884.270.68281.2
2026.03
72.886.180.69185.88672.18482.3
2026.04
72.7884.0679.6880.3486.6687.1272.358681.12
2025.03
72.7588.5281.1795.2786.4292.5980.9787.885.69
2025.07
72.7287.2179.1794.6587.3789.5276.968684.2
2026.03
72.788.380.594.784.489.879.986.684.6
2026.03
72.68679.289.183.584.870.682.881.1
2025.09
72.688.380.0994.3186.4291.9281.1485.285
2024.05
72.584.879.892.184.784.271.282.481.5
2024.05
72.585.379.990.182.982.769.783.680.8
2024.02
72.584.979.892.184.784.271.282.481.4
2024.02
72.585.379.990.182.982.769.783.680.8
2024.08
72.584.979.892.184.784.271.282.481.5
2026.03
72.584.979.892.184.784.271.282.481.4
2024.05
72.484.981.592.484.284.269.682.881.5
2024.05
72.483.879.792.583.985.372.582.681.6
2024.02
72.484.981.592.484.284.269.682.881.5
2024.08
72.484.981.592.484.284.269.682.881.5
2025.05
72.3586.5175.1891.7374.9890.7479.528481.88
2024.07
72.384.278.788.58480.769.183.780.2
2024.06
72.386.779.393.584.887.775.782.882.8
2024.07
72.287.58094.383.984.575.682.482.5
2024.08
72.285.181.294.184.486.673.786.683
2025.05
72.1786.5175.7991.2875.6191.4681.488682.54
2026.04
72.1489.2181.395.1189.4594.5685.328987.01
2024.05
72.183.580.590.583.782.868.382.480.5
2024.02
72.183.580.590.583.782.868.382.480.5
2024.11
72.183.580.580.583.782.868.382.480.5
2024.08
72.183.580.590.583.782.868.382.480.5
2024.08
72.186.381.895.187.286.273.784.283.3
2026.03
72.183.580.590.583.782.868.382.480.5
2025.07
72.0586.5679.8493.8484.6986.3275.178582.93
2024.05
7283.179.989.18384.57181.280.5
2024.02
7283.179.989.18384.57181.280.5
2025.05
71.9382.9279.2288.983.0382.766.988279.71
2024.05
71.88379.288.182.482.567.381.879.5
2024.05
71.883.77689.182.683.768.282.479.7
2024.02
71.88379.288.182.482.567.381.879.5
2024.02
71.883.77689.182.683.768.282.479.7
2024.08
71.88379.288.182.482.567.381.879.5
Showing 100 of 202 rows