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

General Tasks on MMLU-redux

86.8Accuracy

Qwen2.5-72B

69.84874.24978.6583.051Feb 19, 2025May 5, 2025Jul 19, 2025Oct 3, 2025Dec 17, 2025Mar 2, 2026May 17, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2025.02
86.8
2025.02
86.2
2025.02
85.9
2025.02
83
2025.02
81.6
2026.05
76.6
2026.05
76.2
2026.05
75.2
2026.05
75.1
2026.05
74.8
2026.05
73
2026.05
72.8
2026.05
72.6
2026.05
72.4
2026.05
70.5