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

Multiple Choice Question Answering on MMLU-PRO (zero-shot)

84.29Accuracy

Gemini 2.0 Pro Exp

40.006851.50346374.4966May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
84.29
2026.05
82.86
2026.05
82.29
2026.05
80
2026.05
79.71
2026.05
79.14
2026.05
78.57
2026.05
77.71
2026.05
77.43
2026.05
77.14
2026.05
76.57
2026.05
76.57
2026.05
76.29
2026.05
76
2026.05
75.71
2026.05
75.43
2026.05
75.14
2026.05
75.14
2026.05
74.86
2026.05
74
2026.05
73.43
2026.05
71.43
2026.05
70.29
2026.05
70.29
2026.05
69.14
2026.05
68.86
2026.05
68.57
2026.05
68.57
2026.05
68.29
2026.05
68.29
2026.05
67.71
2026.05
67.43
2026.05
66.29
2026.05
66
2026.05
65.71
2026.05
65.14
2026.05
64.86
2026.05
63.14
2026.05
63.14
2026.05
62.86
2026.05
62.29
2026.05
60.57
2026.05
54.57
2026.05
53.71
2026.05
52.29
2026.05
49.71
2026.05
47.14
2026.05
46.86
2026.05
44
2026.05
42
2026.05
41.71