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

Language Understanding on MMLU-M

27.4Accuracy

ZipCal

18.684820.947423.2125.4726Mar 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
27.4-4.89
2026.03
26.29-3.85
2026.03
26.2710.73.83
2026.03
24.44--
2026.03
24.44--
2026.03
24.44--
2026.03
24.44--
2026.03
24.44-0
2026.03
24-0.81
2026.03
23.335,400-
2026.03
23.33-4.07
2026.03
23.19--
2026.03
23.19--
2026.03
23.1110.7-0.08
2026.03
23.01--0.18
2026.03
22.54-0.32
2026.03
22.51--
2026.03
22.44--
2026.03
22.22--
2026.03
22.22--
2026.03
21.96--0.26
2026.03
21.48--
2026.03
21.48--
2026.03
21.48--
2026.03
21.4--
2026.03
21.3--0.1
2026.03
19.26--
2026.03
19.26--
2026.03
19.02--0.24