Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Alternative Annotator Test on Bills
Loading...
85
Doc-Level Fit Prob
PROXANN
27.8
42.65
57.5
72.35
Jul 1, 2025
Doc-Level Fit Prob
Doc-Level Rank Prob
Topic-Level Fit Prob
Topic-Level Rank Prob
Updated 5mo ago
Evaluation Results
Method
Method
Links
Doc-Level Fit Prob
Doc-Level Rank Prob
Topic-Level Fit Prob
Topic-Level Rank Prob
PROXANN
LLM Backbone=GPT-4o
2025.07
85
71
77
75
PROXANN
LLM Backbone=Qwen-3 32B
2025.07
67
68
74
70
PROXANN
LLM Backbone=Llama-3.3...
2025.07
66
67
70
60
PROXANN
LLM Backbone=Qwen-3 8B
2025.07
66
57
80
43
PROXANN
LLM Backbone=Qwen-2.5-72B
2025.07
61
71
78
65
PROXANN
LLM Backbone=Llama-3.1-8B
2025.07
30
53
14
44
Feedback
Search any
task
Search any
task