Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-hop Question Answering on MMhops Comparison (test)

29.39Accuracy

Gemini-2.5-pro

2.93249.801216.6723.5388Dec 15, 2025
Updated 4d ago

Evaluation Results

MethodLinks
29.39
23.18
2025.12
22.01
2025.12
18.27
2025.12
17.02
2025.12
9.72
2025.12
8.76
2025.12
7.59
7.05
2025.12
6.62
2025.12
6.2
2025.12
4.81
2025.12
3.95