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

Language Understanding on MMLU (0-shot)

70.46Accuracy

Token Filtering

21.829634.454847.0859.7052Feb 7, 2024May 28, 2024Sep 17, 2024Jan 7, 2025Apr 28, 2025Aug 18, 2025Dec 8, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
70.46--------------------------63.463.3482.0976.86
2024.02
60.6------------------------------
2024.02
60.2------------------------------
2024.02
59------------------------------
2024.06
54.54--------------------------50.4843.762.7262.74
2024.02
54.5------------------------------
2024.02
54.5------------------------------
2024.02
54.4------------------------------
2024.02
54.3------------------------------
2024.02
53.3------------------------------
2024.02
53------------------------------
2024.05
52.8--------------------------56.942.46155.6
2024.02
52.5------------------------------
2024.05
52.5--------------------------57.441.360.455.8
2024.02
52.4------------------------------
2024.05
52.3--------------------------56.941.560.454.9
2024.02
52.2------------------------------
2024.02
52.1------------------------------
2024.02
51.9------------------------------
2024.05
51.3--------------------------56.340.358.854.6
2024.05
51.1--------------------------55.341.658.153.3
2024.06
51.08--------------------------47.4840.1358.8657.83
2024.06
50.94--------------------------46.6140.8258.7357.59
2025.12
50.59--------------------------45.6543.256.4259.8
2024.02
50.5------------------------------
2024.02
50.5------------------------------
2024.02
50.5------------------------------
2024.02
50.5------------------------------
2024.02
50.2------------------------------
2024.02
50.1------------------------------
2024.02
50------------------------------
2024.05
49.9--------------------------544057.152.5
2025.12
47.44--------------------------43.5140.8854.6352.91
2024.02
47.1------------------------------
2024.02
47.1------------------------------
2024.02
46.8------------------------------
2024.02
46.4------------------------------
2024.02
46.3------------------------------
2024.02
46.3------------------------------
2024.02
46.1------------------------------
2025.12
45.99--------------------------42.8141.4254.3247.69
2024.02
45.9------------------------------
2024.05
45.8------------------------------
2024.05
45.7--------------------------49.737.551.447.8
2024.02
45.6------------------------------
2024.05
45.3------------------------------
2024.05
45.2--------------------------50.337.449.846.8
2024.02
44.3------------------------------
2024.02
43.9------------------------------
2024.02
43.6------------------------------
2024.05
43.6--------------------------48.335.248.845.8
2024.02
43.2------------------------------
2024.02
41.6------------------------------
2024.05
41.2--------------------------42.334.448.142.9
2024.06
41.07--------------------------39.632.5446.0246.11
2024.02
40.9------------------------------
2025.12
40.81--------------------------39.2133.1745.9945.41
2025.12
40.81--------------------------39.2133.1745.9945.41
2024.02
40.7------------------------------
2024.02
40.7------------------------------
2024.05
40.5--------------------------43.333.744.842.9
2024.05
39.9--------------------------40.433.745.942.2
2024.05
39.6------------------------------
2024.05
39.3------------------------------
2024.05
39--------------------------4231.843.641.3
2024.02
38.8------------------------------
2024.05
37.9------------------------------
2024.02
37.5------------------------------
2024.02
36.3------------------------------
2024.02
36.1------------------------------
2024.02
35.8------------------------------
2024.02
34.9------------------------------
2024.02
34.9------------------------------
2024.02
34.9------------------------------
2024.02
34.8------------------------------
2024.02
34.3------------------------------
2024.05
33.5--------------------------34.530.33337.3
2024.02
33.1------------------------------
2025.12
33.06--------------------------29.6931.4334.6838.2
2024.02
32.5------------------------------
2024.02
32.5------------------------------
2024.05
32.5--------------------------33.728.736.332.9
2024.05
31.8--------------------------32.628.931.435.3
2024.05
31.7--------------------------32.627.235.633.2
2024.02
31.5------------------------------
2024.02
31.3------------------------------
2024.02
31------------------------------
2024.02
30.6------------------------------
2024.02
30.6------------------------------
2024.02
30.6------------------------------
2024.05
30.1------------------------------
2024.02
29------------------------------
2024.06
28.12--------------------------26.5726.8130.3528.75
2024.02
28------------------------------
2025.12
27.86--------------------------27.5524.9926.9132.19
2024.02
27.7------------------------------
2024.05
27--------------------------28.825.825.628
2024.02
25------------------------------
2024.02
24.6------------------------------
2024.02
23.7------------------------------
Showing 100 of 116 rows