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

Conversational Ability on MT-Bench (Score and Avg. Time)

7.58MT-Bench Score

Qwen3-32B

3.06644.23825.416.5818Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026Mar 21, 2026Mar 22, 2026Mar 23, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
7.58---
2026.03
7.24---
2026.03
6.88---
2026.03
6.51---
2026.03
6.12---
2026.03
6.01---
2026.03
5.63---
2026.03
5.58---
2026.03
5.52---
2026.03
5.05---
2026.03
5.02---
2026.03
4.86---
4.62---
2026.03
4.6---
2026.03
4.48---
2026.03
4.39---
2026.03
4.39---
2026.03
4.36---
2026.03
4.36---
2026.03
4.33---
2026.03
4.32---
2026.03
4.3---
2026.03
4.12---
2026.03
3.91---
2026.03
3.88---
2026.03
3.84---
2026.03
3.49---
2026.03
3.24---
2026.02
-4.582.461-
2026.02
-4.492.132-
2026.02
-5.032.042-
2026.02
-5.321.802-
2026.02
-5.422.282-
2026.02
-5.442.012-
2024.08
---4.85
2024.08
---4.6
2024.08
---4.79
2024.08
---4.48
2024.08
---4.5
2024.08
---5.11
2024.08
---4.67
2024.08
---5.04
2024.08
---4.92
2024.08
---5.15
2024.08
---5.64
2024.08
---5.11