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

General Knowledge on C-Eval 1.0 (val)

78.68Accuracy

Qwen-1.5 14B

58.899264.034669.1774.3054Jul 23, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.07
78.68
2024.07
74.1
2024.07
68.57
2024.07
68.35
2024.07
68.2
2024.07
68.05
2024.07
67.6
2024.07
64.41
2024.07
62.63
2024.07
62.4
2024.07
60.13
2024.07
59.66