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

Zero-shot Question Answering on QA Suite (PIQA, Winogrande, HellaSwag, ARC-E, ARC-C, LAMBADA)

78.24PIQA Accuracy

QuaRot

47.965655.825363.68571.5447May 19, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.05
78.2468.9873.255.7741.6456.6762.42
2026.05
78.0769.1473.355.8542.4958.0862.82
2026.05
77.6468.6772.7855.0143.0957.562.45
2026.05
77.3768.5972.9454.2141.7258.2462.18
2026.05
76.3366.8569.251.0140.6150.5359.06
2026.05
76.3366.4670.4754.7140.3655.2560.6
2026.05
76.2866.7770.255.5141.7256.1661.11
2026.05
76.2268.3571.2754.1741.8157.0361.48
2026.05
76.0667.8871.7255.2243.1755.7961.64
2026.05
76.0165.5168.5953.9639.4254.8459.72
2026.05
75.9564.8869.3353.6240.4451.7859.33
2026.05
75.4167.4870.0255.9341.9856.9661.3
2026.05
75.4168.2770.0354.4641.0460.6661.65
2026.05
74.9767.2572.0356.1941.8157.0761.55
2026.05
74.4866.5469.5854.6741.5556.3960.54
2026.05
74.3762.2766.1951.0538.7444.456.17
2026.05
74.0566.7769.3655.0141.1355.7760.35
2026.05
73.7864.9667.7751.0538.9153.1758.27
2026.05
73.7266.3869.455.1842.6655.2760.44
2026.05
73.6167.7268.7853.2839.4253.2959.35
2026.05
73.3461.0964.1458.0840.7840.1756.27
2026.05
73.1261.5660.9648.6535.8445.6254.36
2026.05
72.260.4664.548.1536.2638.2753.31
2026.05
72.0962.1964.249.1636.9546.8955.25
2026.05
71.660.9359.3254.3839.9347.3155.58
2026.05
70.6261.8862.5651.9439.3338.8954.2
2026.05
70.460.4662.847.9836.3538.3552.72
2026.05
69.4857.753.4245.4132.5134.9748.98
2026.05
68.7260.1457.153.5439.5944.353.9
2026.05
67.7956.0450.5446.5133.1127.2946.88
2026.05
67.0856.9157.5546.0932.342647.66
2026.05
66.5957.0654.5653.1637.0338.3351.12
2026.05
66.5958.854.6852.1936.0138.0451.05
2026.05
66.5455.9653.8448.4434.7331.9648.58
2026.05
65.8955.8852.9449.0734.4734.6848.82
2026.05
63.9356.5156.241.7929.7829.1546.23
2026.05
63.1752.5741.0536.6229.359.7438.75
2026.05
62.7952.4146.7746.9332.6821.9943.93
2026.05
62.0250.5944.741.7130.124.4438.93
2026.05
60.9450.5941.7940.6127.0512.338.88
2026.05
59.1950.4338.2735.6525.175.0735.63
2026.05
58.650.236.8334.1826.287.5335.6
2026.05
57.9450.0434.6532.8324.7411.1635.23
2026.05
57.8350.5935.4634.0926.0212.536.08
2026.05
56.3750.9133.6431.7324.5712.0934.89
2026.05
51.9651.3824.9326.0124.74029.84
2026.05
51.9650.9127.6826.8925.170.1430.46
2026.05
51.6953.2827.627.2725.341.5131.12
2026.05
51.6350.225.6825.6325.940.0629.86
2026.05
51.0348.7827.3126.1422.950.1929.4
2026.05
50.3349.0125.1824.8322.53028.65
2026.05
50.1650.0425.212525.68029.35
2026.05
5051.1425.3724.2423.46029.04
2026.05
49.8948.9324.9925.2922.610.0428.62
2026.05
49.2450.9125.0625.5124.4029.19
2026.05
49.1349.2527.1726.8125.340.9929.78