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

Comprehensive Examination on GAOKAO (test)

76.3Accuracy

Qwen-14B-Chat

16.08431.71747.3562.983Mar 26, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.03
76.3
2024.03
62.5
2024.03
62.1
2024.03
59.4
2024.03
58.6
2024.03
58.6
2024.03
58.3
2024.03
58
2024.03
57.3
2024.03
57.1
2024.03
56.3
2024.03
52.8
2024.03
51.1
2024.03
45.8
2024.03
45.6
2024.03
42.6
2024.03
40.7
2024.03
40.7
2024.03
37.5
2024.03
34.7
2024.03
32.3
2024.03
28.7
2024.03
28.6
2024.03
23.2
2024.03
19.8
2024.03
19
2024.03
18.4