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

Multi-turn Dialogue on ACEBench En

68MT Accuracy

GPT-4o-2024-11-20

22.2434.124657.88Aug 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
68
61
2025.08
51
48
2025.08
44
2025.08
34
24