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

Zero-shot Classification on (BoolQ, HellaSwag, WinoGrande, ARC-e, ARC-c, PIQA, OBQA)

81.65BoolQ Accuracy

Dense

37.741249.140660.5471.9394Apr 14, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
81.6560.7171.1177.5346.1677.9135.264.32-
78.4752.2467.473.9943.4375.7927.459.82-
2026.04
78.4752.2467.473.9943.4375.7927.459.82-
2026.04
76.1344.8763.0465.7434.3371.8421.9353.9842.86
2026.04
76.0645.0864.5964.5234.2271.1623.3354.14-
2026.04
75.9544.8862.9366.1134.0771.4722.1353.9438.1
2026.04
75.8144.8963.3566.1634.3371.6522.3354.0842.86
2026.04
75.7744.8163.2765.534.371.822.1353.9438.1
2026.04
75.7140.0161.1257.4128.1668.6421.7350.480.95
2026.04
75.5244.7962.8865.4234.371.852253.8238.1
2026.04
74.5543.4361.6464.3733.2570.5121.7352.784.76
2026.04
74.2843.4363.8564.6634.570.2621.2753.18-
2026.04
73.8642.962.6766.2235.0171.421.9353.4361.9
2026.04
73.8643.263.5966.435.3271.2521.653.652.38
2026.04
73.7942.761.8866.2234.1971.4221.9353.1647.62
2026.04
73.3742.8862.7766.3334.771.2722.0753.3457.14
2026.04
73.2142.5762.0466.0233.7970.9622.3352.9942.86
2026.04
73.0442.3860.866.2633.7370.9821.4752.6738.1
2026.04
72.7255.369.2274.3742.4176.7131.260.28-
2026.04
71.8638.5959.9353.6528.2167.1622.7348.8819.05
2026.04
70.3736.959.6755.5727.965.9617.3347.6776.19
2026.04
70.3236.959.6955.8427.3666.2517.4747.6976.19
2026.04
70.1136.5759.5454.1126.6865.8117.847.2361.9
2026.04
70.0836.8458.8355.327.1366.4318.0747.5376.19
2026.04
69.8736.959.9355.2327.3666.4117.9347.6690.48
2026.04
69.7336.6159.353.2726.2265.1617.2746.79-
2026.04
68.7339.3462.2756.5226.9369.1320.3349.0485.71
2026.04
68.1738.6261.9853.372668.0619.84814.29
2026.04
67.7639.1361.0157.5927.7969.442048.9695.24
2026.04
67.5534.856.4149.1324.0664.7816.7344.789.52
2026.04
67.4140.6461.6257.3928.1669.7320.649.3671.43
2026.04
67.2637.1859.0651.8925.5466.4717.246.3733.33
2026.04
66.8238.1460.9153.8926.2867.7518.4747.474.76
2026.04
66.6834.1154.7548.2221.1664.414.5343.4180.95
2026.04
66.6439.8961.9655.5727.5368.7221.248.7928.57
2026.04
66.4134.4957.5151.4625.6564.5416.245.1880.95
2026.04
65.9335.9557.5151.0924.3266.0316.8745.3938.1
2026.04
65.8934.2556.9951.525.7464.3316.6745.0576.19
2026.04
65.6438.3159.9355.6326.1468.3420.8747.8352.38
2026.04
65.5838.0659.355.9926.5667.9420.9347.7747.62
2026.04
65.5434.3357.1448.7225.0663.9816.6744.49-
2026.04
65.3833.9256.9151.0225.1764.2515.8744.6547.62
2026.04
64.9149.561.4366.3934.4175.5426.854.1466.67
2026.04
64.8235.1256.5650.5823.8365.5816.9344.7738.1
2026.04
64.6933.5556.7551.3224.9164.2415.3344.433.33
2026.04
64.4833.0955.6250.7424.9464.181544.0123.81
2026.04
64.3849.0361.365.8234.175.727.3353.9533.33
2026.04
64.2934.1655.8850.8825.2865.2517.1344.738.1
2026.04
64.0532.1754.2243.9520.7161.351741.9219.05
2026.04
64.0147.7360.1465.1531.2374.3226.452.71-
2026.04
63.932.5755.6749.8923.8363.6414.4743.4219.05
2026.04
63.7337.458.9354.3125.6867.051746.366.67
2026.04
63.3836.0557.5154.1525.4366.9616.2745.6861.9
2026.04
62.9228.2252.1234.6918.8657.2912.7338.12-
2026.04
62.728.5751.5135.171958.2911.8738.1657.14
2026.04
62.6328.8352.3335.6919.258.1412.238.4371.43
2026.04
62.628.7751.8336.2718.6958.2312.3338.3961.9
2026.04
62.5928.5351.8335.1619.1158.121238.1957.14
2026.04
62.5928.7952.0135.9719.258.651238.4666.67
2026.04
62.3632.4953.0946.4921.363.2215.7342.157.14
2026.04
62.2932.5353.746.321.9963.1316.642.3666.67
2026.04
62.232.8653.6744.1423.4662.591842.4233.33
2026.04
62.233.6653.5446.3723.4164.0416.442.866.67
2026.04
62.083253.8845.2922.0162.0217.642.1333.33
2026.04
61.9831.4753.0945.3720.2862.1314.3341.2442.86
2026.04
61.9527.1649.9930.8918.0356.3112.2736.669.52
2026.04
61.8130.4751.5140.9220.7160.3613.2739.8666.67
2026.04
61.6929.5652.3339.2819.6560.3212.0739.2785.71
2026.04
61.634.4155.5152.5325.665.417.244.6161.9
2026.04
61.5629.5351.6440.419.661.1213.439.6180.95
2026.04
61.4231.6853.8344.0421.4761.791541.3257.14
2026.04
61.3335.5354.8352.5324.6966.8116.644.6261.9
2026.04
61.2829.8852.0740.2220.8260.0314.839.8733.33
2026.04
61.0828.5150.6238.4119.4359.3612.6738.5871.43
2026.04
60.6732.1654.4644.9421.4762.2117.0741.8542.86
2026.04
58.9628.8651.3538.8218.9459.0513.9338.5619.05
2026.04
58.0128.9251.2237.5619.5159.3213.438.2814.29
2026.04
57.2828.3251.5135.7618.3458.4113.6737.6128.57
2026.04
56.5537.8955.5158.8428.5871.4918.9346.8380.95
2026.04
55.8327.4248.83117.8356.8412.235.7-
2026.04
52.6135.8254.1745.1924.2365.6515.9341.9419.05
2026.04
47.1827.2650.331.751856.6611.7334.752.38
2026.04
46.7627.149.9631.5917.6156.5711.8734.4942.86
2026.04
45.5127.3850.331.817.7857.0511.4734.4752.38
2026.04
45.0826.9349.8331.1417.9556.3111.434.0938.1
2026.04
41.126.8649.731.118.1556.331233.647.62
2026.04
39.4326.8149.4631.1418.5455.8211.6733.2742.86