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

Helpfulness Evaluation on MM-Vet2 (test)

54.4GPT-Eval Score

No Defense

10.61621.98333.3544.717Aug 26, 2025
Updated 16d ago

Evaluation Results

MethodLinks
2025.08
54.4
2025.08
48.9
2025.08
46.8
2025.08
20.4
2025.08
20.2
2025.08
19.3
2025.08
17.7
2025.08
13.1
2025.08
12.9
2025.08
12.3