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

Multiple-choice Question Answering on MMLU-Pro Law

30.8Accuracy

KVZip

-1.2327.08415.423.716Oct 9, 2025
Updated 6d ago

Evaluation Results

MethodLinks
2025.10
30.8
2025.10
27.6
2025.10
27.2
2025.10
27
2025.10
26.8
2025.10
26.2
2025.10
26.2
2025.10
25.8
2025.10
23.4
2025.10
22
2025.10
19
2025.10
17.8
2025.10
15.6
2025.10
13.8
2025.10
13.8
2025.10
12.6
2025.10
12
2025.10
11.8
2025.10
11.4
2025.10
10.8
2025.10
10.6
2025.10
9.8
2025.10
9.8
2025.10
9.6
2025.10
9
2025.10
9
2025.10
7.6
2025.10
7.4
2025.10
3.8
2025.10
3.8
2025.10
3
2025.10
2.4
2025.10
2.4
2025.10
1.8
2025.10
0.8
2025.10
0.4
2025.10
0.2
2025.10
0.2
2025.10
0
2025.10
0