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

Multi-task Language Understanding on CEval

82.5Accuracy

Base Model(Qwen3-8B-Base)

23.2238.615469.39Jan 11, 2024Jun 4, 2024Oct 27, 2024Mar 21, 2025Aug 13, 2025Jan 5, 2026May 31, 2026
Updated 22h ago

Evaluation Results

MethodLinks
2026.05
82.5
2026.05
82.4
2026.05
82.1
2026.05
81.3
2026.05
77.9
2026.05
72.51
2026.05
68.72
2024.01
44.7
2025.02
44
2024.01
40.6
2024.01
40.3
2024.01
40
2026.05
38.68
2024.01
37.1
2025.02
36.1
2024.01
35.1
2024.01
33.9
32.8
2026.05
30.99
2025.02
27.2
2024.01
26.2
2025.02
25.5