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

Dialogue on MT-Bench

9.3MT-Bench Score

GPT-4o

5.06726.16617.2658.3639Feb 24, 2025May 16, 2025Aug 6, 2025Oct 27, 2025Jan 17, 2026Apr 9, 2026Jun 30, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.03
9.3
2026.03
9.1
2026.03
9
2026.03
8.9
2026.03
8.6
2026.03
8.5
2026.03
8.2
2026.04
8.138
2026.04
7.975
2026.04
7.862
2026.04
7.837
2026.04
7.831
2026.04
7.812
2026.04
7.793
2026.04
7.762
2026.04
7.756
2026.04
7.725
2026.04
7.681
2026.04
7.681
2026.04
7.506
2026.04
7.162
2026.06
6.39
2026.06
6.32
2026.06
6.3
2026.06
6.27
2025.08
6.26
2026.06
6.21
2026.06
6.2
2026.06
6.18
2025.08
6.16
2026.06
6.16
2026.06
6.12
2025.08
6.1
2026.06
6.1
2026.06
6.08
2025.08
6.05
2025.02
6.01
2025.08
6.01
2026.06
6
2025.08
5.98
2025.02
5.97
2025.08
5.97
2025.08
5.97
2026.06
5.97
2026.06
5.95
2025.08
5.94
2025.08
5.92
2026.06
5.92
2026.06
5.88
2025.02
5.84
2025.02
5.82
2025.08
5.8
2025.08
5.8
2026.06
5.78
2026.06
5.72
2026.06
5.72
2026.06
5.71
2025.02
5.61
2026.06
5.61
2026.06
5.61
2026.06
5.57
2025.02
5.56
2025.02
5.3
2026.06
5.3
2026.06
5.3
2026.06
5.25
2025.02
5.23