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

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

76.19MT-Bench Score

Qwen3-Omni-30B-A3B-Thinking

3.161222.120641.0860.0394Oct 28, 2024Jan 30, 2025May 4, 2025Aug 6, 2025Nov 8, 2025Feb 10, 2026May 15, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2025.09
76.19
2025.09
74.5
2025.09
71.5
2025.09
70.81
2025.09
67.62
2025.09
65.88
2025.09
65
2025.09
64.56
2025.09
64.12
2025.09
59.81
2025.09
54.62
2026.05
9
2025.07
8.99
2025.07
8.97
2025.07
8.9
2025.07
8.89
2026.05
8.81
2025.07
8.8
8.8
2025.07
8.79
2025.07
8.68
2024.10
8.67
2026.05
8.65
2024.10
8.64
2025.07
8.64
2025.07
8.62
2025.07
8.61
2024.10
8.58
2024.10
8.57
2025.07
8.56
2025.07
8.55
2025.07
8.54
2026.05
8.5
2026.05
8.5
2025.07
8.47
2025.07
8.46
2026.05
8.3
2026.05
8.3
2026.05
8.2
2026.05
8.2
2026.05
8.2
2026.05
8.2
2026.05
8.2
2026.05
8.2
2026.05
8.2
2025.07
8.18
2025.07
8.13
2025.07
8.1
2026.05
8.1
2026.05
8.1
2025.07
8.07
2025.07
8.04
2025.07
8.02
2025.07
8.01
2025.07
8.01
2026.05
8
2026.05
8
2026.05
8
2026.05
8
2026.05
8
2026.05
8
2026.05
8
2024.10
7.97
2024.10
7.95
2025.07
7.92
2024.10
7.85
2026.05
7.8
2026.05
7.7
2026.05
7.7
2026.05
7.7
2025.07
7.63
2026.05
7.6
2026.05
7.6
2025.07
7.59
2025.07
7.57
2025.07
7.52
2025.07
7.51
2026.05
7.5
2026.05
7.5
2026.05
7.5
2025.07
7.39
2025.07
7.29
2025.07
7.06
2025.07
6.92
2025.07
6.86
2026.05
6.35
2026.05
6.31
2026.05
6.26
2026.05
6.24
2026.05
6.23
2026.05
6.19
2026.05
6.18
2026.05
6.16
2026.05
6.15
2026.05
6.13
2026.05
6.12
2026.05
6.08
2026.05
6.01
2026.05
5.99
2026.05
5.97
Showing 100 of 126 rows