Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Instruction Following on MT-Bench v1.0 (test)

61.2MT-Bench Score

CaR

1.639217.102132.56548.0279Apr 3, 2024May 25, 2024Jul 16, 2024Sep 7, 2024Oct 29, 2024Dec 20, 2024Feb 11, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.02
61.2--
2025.02
60.8--
2025.02
60.3--
2025.02
60.1--
2025.02
59.8--
2025.02
59.5--
2025.02
59.3--
2025.02
59.2--
2025.02
58.8--
2025.02
58.5--
2025.02
58.4--
2025.02
57.5--
2025.02
50.3--
2025.02
50.2--
2025.02
50.1--
2025.02
49.8--
2025.02
49.5--
2025.02
49.5--
2025.02
49.5--
2025.02
49.3--
2025.02
48.6--
2025.02
48.5--
2025.02
48.4--
2025.02
48.3--
2025.02
48.3--
2025.02
47.9--
2025.02
47.8--
2025.02
47.8--
2025.02
42.2--
2025.02
40.6--
2024.04
6.67--
2024.04
6.65--
2024.04
6.65--
2024.04
6.64--
2024.04
6.3--
2024.04
6.27--
2024.04
6.27--
2024.04
6.23--
2024.04
5.82--
2024.04
5.71--
2024.04
5.69--
2024.04
5.51--
2024.04
5.46--
2024.04
5.21--
2024.04
5.16--
2024.04
4.96--
2024.04
4.87--
2024.04
4.79--
2024.04
4.76--
2024.04
4.73--
2024.04
4.41--
2024.04
3.93--
2024.06
-90.011.02
2024.06
-89.251.58
2024.06
-43.081.89
2024.06
-62.152.03
2024.06
-64.312.11
2024.06
-81.50.91
2024.06
-86.21.46
2024.06
-30.111.71
2024.06
-52.821.82
2024.06
-54.831.89