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

Multitask Language Understanding on MMLU (test)

92.16Accuracy

Claude 3.5 Sonnet

61.417669.398877.3885.3612Mar 29, 2022Nov 17, 2022Jul 9, 2023Feb 28, 2024Oct 19, 2024Jun 10, 2025Jan 30, 2026
Updated 2d ago

Evaluation Results

MethodLinks
92.161.84-----------------------------------------------------------------
2024.06
91.611.81-----------------------------------------------------------------
2025.05
90------------------------------------------------------------------
89.8------------------------------------------------------------------
89.752.45-----------------------------------------------------------------
2025.05
89------------------------------------------------------------------
2025.05
89------------------------------------------------------------------
2025.05
88------------------------------------------------------------------
2024.06
87.282.34-----------------------------------------------------------------
2025.05
87------------------------------------------------------------------
2025.05
87------------------------------------------------------------------
2025.05
87------------------------------------------------------------------
2023.07
86.4------------------------------------------------------------------
2025.05
85------------------------------------------------------------------
2025.05
85------------------------------------------------------------------
2025.05
84------------------------------------------------------------------
2024.06
83.312.93-----------------------------------------------------------------
2024.06
82.632.84-----------------------------------------------------------------
2026.01
82.15------------------------------------------------------------------
2025.05
82------------------------------------------------------------------
2025.05
82------------------------------------------------------------------
2024.06
81.452.89-----------------------------------------------------------------
2025.05
80------------------------------------------------------------------
2025.05
80------------------------------------------------------------------
2023.07
78.3------------------------------------------------------------------
2025.05
78------------------------------------------------------------------
2025.05
77------------------------------------------------------------------
2025.12
76.9------------------------------------------------------------------
2026.01
75.56------------------------------------------------------------------
2022.10
75.2------------------------------------------------------------------
2025.05
75------------------------------------------------------------------
2025.05
75------------------------------------------------------------------
2025.05
75------------------------------------------------------------------
2025.05
75------------------------------------------------------------------
2025.05
74------------------------------------------------------------------
2025.05
73------------------------------------------------------------------
2026.01
72.29------------------------------------------------------------------
2022.10
72.2------------------------------------------------------------------
2023.01
72.2------------------------------------------------------------------
2025.05
72------------------------------------------------------------------
2025.05
72------------------------------------------------------------------
2023.01
71.8---------------------------------------------------------76.579.958.973.2-----
2024.03
71.8------------------------------------------------------------------
2023.01
71.4---------------------------------------------------------7679.758.872.1-----
2025.05
71------------------------------------------------------------------
2022.10
70.7------------------------------------------------------------------
2022.10
70.2------------------------------------------------------------------
2023.07
70------------------------------------------------------------------
2025.05
70------------------------------------------------------------------
2023.11
69.58------------------------------------------------------------------
2022.10
69.5------------------------------------------------------------------
2022.10
69.3------------------------------------------------------------------
2022.10
69.3------------------------------------------------------------------
2023.02
69.3---------------------------------------------------------778155.669.6-----
2023.01
69.3---------------------------------------------------------778155.669.6-----
2023.07
69.3------------------------------------------------------------------
2023.11
69.18------------------------------------------------------------------
2025.05
69------------------------------------------------------------------
2025.05
69------------------------------------------------------------------
2025.05
69------------------------------------------------------------------
2025.05
69------------------------------------------------------------------
2023.11
68.93------------------------------------------------------------------
2023.07
68.9------------------------------------------------------------------
2023.07
68.9------------------------------------------------------------------
2023.11
68.81------------------------------------------------------------------
2023.11
68.66------------------------------------------------------------------
2023.11
68.64------------------------------------------------------------------
2023.11
68.53------------------------------------------------------------------
2023.11
68.43------------------------------------------------------------------
2023.11
68.41------------------------------------------------------------------
2023.11
68.32------------------------------------------------------------------
2023.01
68.3---------------------------------------------------------74.276.957.870.1-----
2025.05
68------------------------------------------------------------------
2025.05
68------------------------------------------------------------------
2023.11
67.96------------------------------------------------------------------
2024.03
67.9------------------------------------------------------------------
2023.11
67.82------------------------------------------------------------------
2023.11
67.78------------------------------------------------------------------
2024.03
67.7------------------------------------------------------------------
2022.10
67.6------------------------------------------------------------------
2022.03
67.6------------------------------------------------------------------
2022.08
67.5---------------------------------------------------------63.679.35573.9-----
2023.02
67.5---------------------------------------------------------63.679.354.973.9-----
2025.12
66.9------------------------------------------------------------------
2026.01
66.61------------------------------------------------------------------
2022.08
66---------------------------------------------------------61.177.253.274.4-----
2025.05
66------------------------------------------------------------------
2025.05
66------------------------------------------------------------------
2025.05
66------------------------------------------------------------------
2024.03
65.8------------------------------------------------------------------
2022.10
64.5------------------------------------------------------------------
2024.07
64.34------------------------------------------------------------------
2024.03
64------------------------------------------------------------------
2024.03
64------------------------------------------------------------------
2024.03
64------------------------------------------------------------------
63.4------------------------------------------------------------------
2023.02
63.4---------------------------------------------------------61.872.951.767.4-----
2023.07
63.4------------------------------------------------------------------
2024.03
62.7------------------------------------------------------------------
2023.07
62.6------------------------------------------------------------------
Showing 100 of 333 rows