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

Multi-task Language Understanding on CEval

91.21Accuracy

Qwen3 Model

22.871640.613358.35576.0967Jan 11, 2024Jun 4, 2024Oct 27, 2024Mar 21, 2025Aug 13, 2025Jan 5, 2026May 31, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
91.21
2026.05
82.5
2026.05
82.4
2026.05
82.1
2026.05
81.3
2025.09
78.7
2026.05
77.9
2025.09
76.76
2026.05
72.51
2025.09
72.02
2025.09
70.45
2026.05
68.72
2025.09
62.62
2025.09
58.02
2024.01
44.7
2025.02
44
2025.09
41.38
2025.09
41.14
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