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

Multi-Hop Question Answering on 2Wiki (test) using Accuracy (%)

45.1Accuracy

GRPO w/ PaW

26.79631.54836.341.052Jun 1, 2026Jun 6, 2026Jun 12, 2026Jun 18, 2026Jun 24, 2026Jun 30, 2026Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.06
45.1
2026.07
45
2026.06
43.6
2026.07
43.6
2026.06
42.8
2026.06
41.2
2026.06
40.1
2026.06
40.1
2026.07
40.1
2026.06
39.5
2026.06
38
2026.07
37
2026.07
36.6
2026.07
36.4
2026.06
35.2
2026.07
35.2
2026.06
34.4
2026.07
32
2026.06
31.9
2026.07
31.9
2026.06
30
2026.07
30
2026.07
29.2
2026.07
27.5