Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Zero-shot Reasoning on Reasoning Suite (PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c) (val test)

81.77PIQA

Dense

64.630869.080473.5377.9796Jun 15, 2024Sep 23, 2024Jan 2, 2025Apr 13, 2025Jul 22, 2025Oct 31, 2025Feb 9, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2024.06
81.7764.8474.5184.2257.3472.54
2025.06
80.5279.3672.377.5349.2371.79
2025.06
80.5279.3672.377.5349.2371.79
2026.02
80.4779.3972.2277.4849.2371.76
2024.06
79.7160.1972.6180.0950.3468.59
2025.05
79.760.272.680.150.468.6
2026.02
79.2276.9266.4662.1642.6665.48
2025.06
79.1175.9968.8274.5846.2568.95
2026.02
79.1175.9969.0674.5846.2569
2026.02
79.1175.9969.0674.5846.2569
2025.06
78.1874.1169.8572.7746.3368.25
2024.06
78.0257.1768.4376.343.5164.69
2025.06
77.5874.2970.2474.1645.5668.37
2025.06
77.5873.4370.4873.1944.9767.93
2025.06
77.5373.9470.8873.2344.868.07
2026.02
77.4872.1868.2772.9842.7566.73
2026.02
77.4867.1361.8865.7838.4862.15
2026.02
77.268.0766.370.4542.9264.99
2026.02
77.0971.366.371.3641.8965.59
2025.06
76.9374.7769.6170.1247.6167.81
2026.02
76.9372.266.365.8241.3864.53
2025.06
76.8269.8865.1961.8335.7561.89
2025.06
76.7771.7170.5673.445.0567.5
2026.02
76.6666.1361.1764.8637.8861.34
2025.06
76.571.1970.3273.3244.4567.16
2024.06
76.4952.6964.4867.7636.7759.64
2025.06
76.4468.4164.9662.2536.661.73
2025.06
76.3966.7860.763.4738.1461.1
2025.06
76.3970.266.368.0142.3264.64
2026.02
76.3373.4471.1172.144.5467.5
2025.05
76.2854.371.2775.8443.964.32
2025.06
76.2268.2763.6158.7136.5260.67
2026.02
76.2269.5968.1971.7141.8965.52
2025.05
76.1754.9272.1476.1843.9464.67
2025.05
76.154.271.775.743.664.26
2025.06
76.0667.1465.5959.0935.0760.59
2024.06
76.0151.864.3367.9336.8659.39
2025.05
75.75472.275.843.864.3
2024.06
75.6849.9462.3564.936.657.89
2024.06
75.0349.6962.1967.3432.2557.3
2025.06
75.0366.4266.0670.0338.4863.2
2026.02
74.9773.0168.7567.445.0566.24
2025.06
74.7166.1267.1771.3841.0464.1
2024.06
74.764.2961.9657.4936.6959.03
2024.06
74.6446.9360.2266.1634.1356.42
2026.02
74.5970.7467.464.4441.9863.83
2024.06
74.4846.6263.6965.734.356.96
2025.06
74.3766.9167.462.8836.6961.65
2026.02
74.2165.8762.4361.0737.2960.17
2024.06
74.146.6158.1764.3133.6255.36
2025.06
73.9469.7267.468.3541.9864.28
2024.06
73.8850.0862.1967.0934.4757.54
2025.06
73.8363.9268.3565.6139.2562.19
2026.02
73.7266.866.6166.1241.9863.05
2025.06
73.6762.9963.361.9533.6259.1
2025.06
73.5669.463.361.8340.2761.67
2026.02
73.0762.4758.9656.4833.0256.8
2025.05
72.9146.4569.1467.3436.0158.37
2024.06
72.7445.7555.7261.3631.0653.33
2026.02
72.7468.4566.5463.4341.362.49
2026.02
72.7467.870.860.3541.362.6
2026.02
72.4260.4459.2754.3434.5656.21
2024.06
72.3645.158.859.6430.0353.19
2025.05
72.245.66869.735.258.14
2025.05
72.147.768.570.33859.22
2025.05
72.0346.0368.5169.9136.1858.53
2024.06
71.8745.1759.5166.536.5255.91
2026.02
71.7159.3155.5653.733.2854.71
2024.06
71.5440.7155.462.1628.9251.75
2025.06
71.2758.4259.6752.1533.6255.03
2024.06
70.8444.1159.4362.9634.0454.28
2024.06
70.5641.0959.9859.9729.0152.12
2024.06
70.442.7352.7257.2429.9550.61
2026.02
70.456.3558.6446.8932.8553.03
2024.06
70.2940.4553.0453.0327.348.82
2024.06
70.2956.4760.0653.234.8154.97
2026.02
70.2462.6365.956.0636.0958.18
2026.02
69.7558.0961.4858.0833.0256.08
2024.06
69.5841.5257.7753.9928.5850.29
2024.06
69.5839.4753.9857.2428.6749.79
2026.02
69.5358.8762.1243.632.1753.26
2026.02
69.4261.564.3356.2735.2457.35
2025.05
68.7240.0362.5161.9530.252.68
2025.06
68.7260.6558.6453.0330.7254.35
2024.06
68.6140.856.6754.827.8249.74
2026.02
68.3962.8959.2756.9937.4657
2026.02
68.3454.0860.4655.3935.8454.82
2026.02
68.2851.558.5652.928.551.95
2025.06
68.1254.1965.9854.3432.7655.08
2024.06
68.0138.7552.6452.3626.2847.61
2024.06
67.9535.8153.1253.9126.3647.43
2025.06
67.8552.5862.4361.8733.755.69
2026.02
67.364249.8854.1728.5848.4
2024.06
67.335.4751.9348.2321.8444.95
2025.06
67.2556.9867.6462.9239.5158.86
2024.06
67.0835.8454.3853.5426.4547.46
2024.06
67.0336.4252.4150.1724.1546.04
2024.06
66.740.1654.349.8326.5347.5
2025.06
65.7853.0462.9856.135.1554.61
2024.06
65.2956.7760.0642.6831.7451.31
Showing 100 of 119 rows