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

Zero-shot Reasoning on ARC-C, ARC-E, BoolQ, Hella, OBQA, PIQA, SIQA, Wino

65.53ARC-C Accuracy

Baseline

20.716432.350743.98555.6193Apr 15, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
65.5384.2688.6986.465084.2246.9377.5172.95
2026.04
60.682.789.478.746.280.144.572.869.4
2026.04
58.3680.8187.0680.3546.881.9945.3976.9569.72
2026.04
55.279.7185.4179.544581.0742.2773.8867.76
2026.04
54.178.4183.8278.5243.881.0142.3773.1666.9
2026.04
54.0178.5884.3178.9243.680.1442.2774.7467.07
2026.04
53.7579.8886.1268.3542.875.4639.169.9364.42
2026.04
53.4177.0684.5378.154381.0141.4574.2766.61
2026.04
53.3366.1288.5379.850.478.0242.5376.466.89
2026.04
53.2474.7580.0978.4743.879.4341.8673.2465.61
2026.04
53.077984.0778.9144.280.5241.5674.5166.98
2026.04
52.9978.0785.2978.5543.279.7641.7673.9566.7
2026.04
52.5676.8584.53774179.6539.7173.7265.63
2026.04
52.377.985.1778.7943.680.4141.274.3566.72
2026.04
52.1364.186.1876.7945.877.3141.573.464.65
2026.04
51.3775.9380.9276.3641.478.7840.0270.864.45
2026.04
51.2874.6277.6872.65407936.961.461.69
2026.04
51.0275.0879.6377.9644.877.5840.7470.2464.63
2026.04
5075.1382.7876.2742.680.0340.3872.6964.99
2026.04
49.0676.1884.0176.234178.2940.1772.7764.71
2026.04
48.6374.7582.5776.994278.8939.5172.6164.49
2026.04
46.9355.0984.574.1844.672.4739.4167.860.62
2026.04
46.1671.5980.9275.274179.4339.1571.6763.15
2026.04
45.8269.5373.1877.1743.879.4939.4670.3262.35
2026.04
44.5465.7475.6371.3837.477.0435.9869.6959.67
2026.04
43.7754.583.8573.144.272.5237.3663.9359.16
2026.04
43.666.2569.9165.213676.7136.0357.5456.41
2026.04
42.6655.2672.2966.883972.4735.7766.7756.39
2026.04
39.5152.2381.1368.1740.468.0636.6965.1956.42
2026.04
38.5766.7976.1262.3934.872.9134.1466.4656.52
2026.04
37.5461.0768.2961.6735.471.637.157.2253.74
2026.04
37.2958.567.7164.7635.471.6536.1360.0653.94
2026.04
36.3563.3863.2766.1339.476.0635.7264.455.59
2026.04
36.0154.3471.4764.8635.670.5137.4160.353.81
2026.04
36.0156.975.0263.153672.7434.959.2754.25
2026.04
34.6460.6158.6565.1534.273.0735.0161.6452.87
2026.04
33.752.172.4559.2636.268.6635.3656.3551.76
2026.04
32.5941.7158.4743.7629.257.7834.3955.0144.11
2026.04
31.5750.6763.5859.9932.471.9333.8858.4150.3
2026.04
30.2955.5158.1755.7330.871.3835.3156.5149.21
2026.04
29.138.2650.8341.4830.258.8132.551.4641.58
2026.04
27.3936.6249.3341.2929.257.9433.6752.5741
2026.04
26.1133.2150.1236.382457.5134.0850.0438.93
2026.04
26.0236.0750.0637.012857.0733.3251.6239.9
2026.04
25.9426.4738.1725.9630.653.9734.4949.6435.66
2026.04
25.9438.7251.9646.7930.858.6534.5452.6442.51
2026.04
25.6825.4240.0926.992451.235.0148.2234.58
2026.04
25.4335.6559.7940.5723.860.4534.751.1441.44
2026.04
25.4330.9344.1930.3525.458.3235.5250.1237.53
2026.04
24.5727.1937.8326.7128.252.2334.0851.0735.23
2026.04
24.4929.838.4426.772852.9433.8847.5135.23
2026.04
24.1544.2839.8237.5528.660.9434.1453.9940.43
2026.04
23.4632.8748.131.752656.6933.4748.5437.61
2026.04
22.4429.5543.9126.9623.453.2635.6252.0135.89