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

LLM-as-a-judge on Chatbot Arena

94.3Coverage

Heuristic Selection

47.70859.80471.983.996May 14, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.05
94.312.6
2026.05
88.436.1
2026.05
85.277.9
2026.05
84.874
2026.05
84.874.4
2026.05
83.672.3
2026.05
83.470
2026.05
56.492.7
2026.05
56.287.1
2026.05
52.490.8
2026.05
51.890.2
2026.05
49.589.6