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

Large Language Model Evaluation on MMLU, GSM8k, HellaSwag, WinoGrande

78.9Average Score

FP16

29.489642.317355.14567.9727Sep 27, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
78.9-----
2025.09
78.73----99.74
2025.09
78.65----99.64
2025.09
78.58----99.55
2025.09
78.53----99.48
2025.09
76.66----97.12
2025.09
76.1----96.5
2025.09
75.74----95.96
2025.09
75.6----95.7
2025.09
75.6----95.8
2025.09
75.32----95.42
2025.09
75.3----95.4
2025.09
75.3----95.4
2025.09
75.13----95.18
2025.09
75.1----95.1
2025.09
74.8----94.8
2025.09
74.2----94
2025.09
74.1----93.9
2025.09
74----93.8
2025.09
73.7----93.3
2025.09
72.9----92.3
2025.09
72.51----91.86
2025.09
71.6----90.7
2025.09
70.78----89.66
2025.09
70.5----89.3
2025.09
69.5----88.1
2025.09
68.91----87.3
2025.09
66.3----84
2025.09
63.05----79.87
2025.09
53.4746.246.3259.7861.56-
2025.09
52.845.944.259.861.399.55
2025.09
52.6345.84559.160.699.22
2025.09
52.545.444.959.660.198.99
2025.09
52.546.144.759.559.598.99
2025.09
46.7436.6933.3657.9558.9687.42
2025.09
46.738.9932.9856.6658.1787.35
2025.09
46.5732.7237.657.5358.4187.09
2025.09
46.0527.8538.5157.5260.386.12
2025.09
45.8237.7929.855.4860.2285.71
2025.09
45.7135.4731.1657.0259.1985.5
2025.09
45.5633.4132.5257.1259.1985.21
2025.09
45.2338.2829.9554.2758.4184.59
2025.09
45.228.1236.8557.0458.884.55
2025.09
45.0137.1527.655.9459.3584.19
2025.09
44.8736.0831.3954.7757.2283.91
2025.09
44.2835.6828.1354.658.7282.83
2025.09
43.6537.3326.0852.6258.5681.64
2025.09
43.2832.825.0256.2459.0480.94
2025.09
43.0134.4825.5553.9858.0180.44
2025.09
42.6629.4427.654.8958.7279.8
2025.09
39.7930.8919.4151.6457.2274.42
2025.09
38.8321.8123.1254.9655.4172.62
2025.09
36.626.8413.549.2956.7568.45
2025.09
36.4415.620.3253.3456.5168.16
2025.09
36.230.4611.8348.2854.2267.7
2025.09
35.6523.4213.2750.0255.8866.67
2025.09
31.7421.854.5545.0755.4959.37
2025.09
31.3913.179.4848.9153.9958.71