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

Language Understanding on MMLU (Accuracy)

96.6Accuracy

M2CL

79.85684.20388.5592.897Jun 9, 2023Nov 22, 2023May 6, 2024Oct 20, 2024Apr 4, 2025Sep 17, 2025Mar 3, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.02
96.6-
2026.02
95.9-
2026.02
95.6-
2026.02
94.6-
2026.02
94.5-
2025.12
94.1-
2026.02
93.9-
2026.02
93.5-
2025.12
93.5-
2026.02
93.2-
2026.02
93-
2026.02
92.7-
2026.02
92.4-
92.4-
2026.02
91.4-
91.4-
2026.03
90.12-
90-
2026.03
89.9-
2026.01
89.54-
2026.03
89.1-
2026.01
88.9-
2026.01
88.9-
88.9-
2026.02
88.7-
2026.01
88.59-
2026.02
88.1-
2026.02
88-
2026.02
88-
2026.03
87.3-
2026.01
87.1-
2026.01
86.92-
2026.03
86.92-
2026.02
86.9-
2026.02
86.8-
2026.02
86.7-
2023.06
86.4-
2024.07
86.4-
2024.08
86-
2026.01
85.69-
2026.01
85.62-
85.62-
2026.01
85.24-
2024.07
85.2-
2026.01
85.17-
2026.01
85.07-
2026.03
85.07-
2026.01
85.04-
2026.01
84.96-
2026.03
84.96-
2026.02
84.9-
2026.01
84.85-
2026.02
84.6-
2026.01
84.4-
84.4-
2026.01
84.31-
2026.03
84.31-
2026.01
84.26-
2024.07
84.2-
2024.08
84.2-
2026.02
84.2-
2026.02
84.2-
2026.01
84.13-
2025.12
84.1-
2026.02
83.9-
2024.07
83.7-
2026.01
83.66-
2026.03
83.66-
2026.01
83.61-
2026.03
83.6-
2025.12
83.5-
2026.01
83.41-
2026.01
83.27-
2026.02
83.2-
2026.02
83.1-
2026.01
83.01-
2026.03
83.01-
2026.02
83-
2026.02
83-
2026.02
82.9-
2025.12
82.9-
2026.01
82.82-
2026.02
82.58-
2026.01
82.35-
2026.03
82.35-
2026.02
82.1-
2026.03
81.95-
2024.08
81.9-
2026.01
81.69-
2026.03
81.69-
2026.01
81.65-
2026.02
81.4-
2026.02
81.3-
2025.12
81.3-
2024.07
81.1-
2026.01
81.04-
2026.03
81.04-
2023.11
80.61-
2026.03
80.61-
2024.08
80.5-
Showing 100 of 844 rows
...