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

Multi-task Language Understanding on MMLU Pro (Accuracy and Length)

57.6Accuracy

RL

3.10417.25231.445.548Jun 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.06
57.6954
2025.06
56.42,173
2025.06
54.64,869
2025.06
53.13,325
2025.06
44.2650
2025.06
39.4549
2025.06
38.1357
2025.06
33.74,300
2025.06
32.8945
2025.06
31.71,724
2025.06
31.41,075
2025.06
28.21,558
2025.06
23.55,405
2025.06
5.21,982