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

General Utility Evaluation on MT_Bench

82.7Agreement Rate

C2PO

31.53244.81658.171.384Dec 29, 2025Jan 23, 2026Feb 17, 2026Mar 14, 2026Apr 8, 2026May 3, 2026May 28, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2025.12
82.7
2026.05
81.72
2026.05
81.62
2026.05
81.62
2026.05
81.51
2026.05
80.98
2026.05
80.87
2026.05
80.55
2026.05
80.55
2026.05
80.34
2026.05
80.02
2026.05
79.91
2026.05
79.91
2025.12
79.9
2025.12
79.9
2026.05
79.76
2026.05
78.8
2026.05
77.15
2025.12
77.1
2026.05
75.24
2025.12
74.2
2026.05
74.18
2026.05
73.06
2026.05
71.04
2025.12
67.3
2025.12
67
2025.12
64.7
2025.12
64.2
2025.12
60.3
2025.12
48.5
2025.12
45.4
2025.12
39.7
2025.12
33.5