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

Language Understanding on MMLU (Subject Performance)

71.91Average Accuracy

MASA

21.168434.341747.51560.6883Oct 7, 2025Oct 19, 2025Oct 31, 2025Nov 12, 2025Nov 24, 2025Dec 6, 2025Dec 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
71.91-55.53-74.4-----------74.24
2025.10
71.71-55.3-73.79-----------74.1
2025.10
71.47-54.74-72.7-----------72.03
2025.10
67----------------
2025.10
67----------------
2025.10
64----------------
2025.10
64----------------
2025.10
64----------------
2025.10
63----------------
2025.10
63----------------
2025.10
63----------------
2025.10
63----------------
2025.10
63----------------
2025.10
62----------------
2025.10
61----------------
2025.10
59.62------------50.6569.8153.2868.23
2025.10
59----------------
2025.10
59----------------
2025.10
59----------------
2025.10
59----------------
2025.10
58.99-48.33-64.71-----------59.96
2025.10
58.83-47.93-64.03-----------59.9
2025.10
58.54------------50.4668.0552.4166.59
2025.10
58.37------------49.9268.2252.2666.46
2025.10
58.18-47.93-63.21-----------59.16
2025.10
58----------------
2025.10
58----------------
2025.10
58----------------
2025.10
58----------------
2025.10
58----------------
2025.10
58----------------
2025.10
57.88------------49.6466.7252.2466.01
2025.10
57.86------------48.9167.4751.8666.53
2025.10
57.78------------49.766.7951.8466.08
2025.10
57.74------------48.7267.2452.1465.98
2025.10
57.61------------49.0366.5952.0165.92
2025.10
57----------------
2025.10
57----------------
2025.10
57----------------
2025.10
56----------------
2025.10
54----------------
2025.10
54----------------
2025.10
54----------------
2025.10
53----------------
2025.12
29.3--3030.5---35.532.131.529.219----
2025.12
28--26.731.2---36.829.526.227.318----
2025.12
26--32.125.2---28.327.12824.117----
2025.10
24.85------------23.9126.124.5924.94
2025.10
24.26------------23.8824.3725.0823.27
2025.10
23.12------------21.8221.7124.2924.04
2024.02
-7689.766.780.785-----------
2024.02
-3973.646.470.179-----------
2024.02
-3582.654.469.378-----------
2024.02
-4769.440.460.768-----------
2024.02
-1457.828.141.958-----------
2024.02
-31703043.665-----------
2024.02
-3476.950.965.974-----------
2024.02
-3470.236.959.570-----------
2024.02
-4174.453.567.674-----------
2024.02
-2768.633.365.967-----------
2024.02
-3381.852.667.677-----------
2026.02
----39.3-49.650---------
2026.02
----39.7-5049---------
2026.02
----40.5-51.152---------
2025.06
-------------37.551.541.649.7
2025.06
-------------38.550.841.249.1
2025.06
-------------38.550.841.949.3
2025.06
-------------38.853.542.250.7
2025.06
-------------68.482.563.276.4
2025.06
-------------68.581.56374.4
2025.06
-------------68.581.763.375.5
2025.06
-------------68.682.763.876.5