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

Accuracy on MMLU-Pro

65.59Accuracy

HuggingGPT

-0.616416.571833.7650.9482Aug 11, 2025Sep 14, 2025Oct 19, 2025Nov 22, 2025Dec 27, 2025Jan 30, 2026Mar 6, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.03
65.59
2026.03
64.64
2026.03
64.16
2026.03
63.66
2026.03
63.04
2025.10
58.7
2025.09
56.6
2025.09
55.4
2025.09
55.2
2025.09
54.9
2025.10
53
2025.10
52.1
2025.09
52
2025.10
51.9
2026.03
51.73
2025.09
50.8
2026.03
50.08
2025.10
49.6
2025.10
47.9
2025.10
47.6
2025.10
46.9
2025.10
46.5
2025.10
44.4
2025.10
43.3
2025.10
42.71
2025.10
42.6
2025.09
42.4
2025.10
42
2025.10
41.7
2025.09
41.3
2025.10
41.21
2025.08
40
2025.09
39.92
2025.09
38.49
2025.09
37.85
2025.10
37.71
2025.09
36.53
2025.09
34.62
2025.10
34.5
2025.10
32.7
2025.08
32.3
2025.09
31.8
2025.08
31.7
2025.09
30.8
2025.08
30.7
2025.09
30.2
2025.08
28.7
2025.09
28.17
2025.09
27.81
2025.08
24.7
2025.09
24.61
2025.09
23.95
2025.10
16.9
2025.10
2.07
2025.10
1.93