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

Language Understanding on MMLU

82.33RA

CortexDebate

23.954839.109954.26569.4201Jul 18, 2023Dec 19, 2023May 21, 2024Oct 22, 2024Mar 25, 2025Aug 26, 2025Jan 27, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.07
82.33
2025.07
77.33
2025.07
75
2025.07
74
2025.07
73
2025.07
71.67
2025.07
71.33
2025.07
69.33
2023.07
68.9
2023.07
63.4
2023.07
62.6
2026.01
62.5
2026.01
60
2023.08
58.2
2023.07
57.8
2023.07
55.4
2023.07
54.8
2023.08
54.2
2023.08
51
2023.08
50.7
2023.08
49.9
2023.08
47.9
2023.07
46.9
2023.07
46.9
2023.08
46.8
2023.07
45.3
2023.08
42.3
2023.07
35.1
2023.08
35.1
2023.07
26.8
2023.07
26.2