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

Multi-turn Dialogue on MT-Bench (GPT-4 Score)

8.9GPT-4 Score

UAPO

7.1327.5918.058.509Sep 3, 2025
Updated 8d ago

Evaluation Results

MethodLinks
2025.09
8.9
2025.09
8.9
2025.09
8.8
2025.09
8.7
2025.09
8.7
2025.09
8.7
2025.09
8.6
2025.09
8.5
2025.09
8.5
2025.09
8.3
2025.09
8.3
2025.09
8.3
2025.09
8.2
2025.09
8.2
2025.09
8.2
2025.09
8.2
2025.09
8.2
2025.09
8.2
2025.09
8.2
2025.09
8.1
2025.09
8
2025.09
7.8
2025.09
7.7
2025.09
7.7
2025.09
7.7
2025.09
7.6
2025.09
7.6
2025.09
7.6
2025.09
7.6
2025.09
7.5
2025.09
7.5
2025.09
7.5
2025.09
7.4
2025.09
7.2