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

LLM Judgment on UltraFeedback

68.75Accuracy

Genii

33.75442.839551.92561.0105Oct 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
68.75
2025.10
65.3
2025.10
64.75
2025.10
63.45
2025.10
63.15
2025.10
62.25
2025.10
62.25
2025.10
62.15
2025.10
61.54
2025.10
59.9
2025.10
59.6
2025.10
58
2025.10
57.25
2025.10
56.7
2025.10
55.95
2025.10
55.3
2025.10
55.3
2025.10
54.65
2025.10
54.1
2025.10
47.7
2025.10
47.2
2025.10
45.95
2025.10
35.1