Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theme Detection on Alberta
Loading...
82.8
Macro F1 Score
Context-based strategy
73.648
76.024
78.4
80.776
Mar 28, 2026
Macro F1 Score
Updated 19d ago
Evaluation Results
Method
Method
Links
Macro F1 Score
Context-based strategy
LLM=Mistral
2026.03
82.8
Zero-CoT
LLM=Mistral
2026.03
81
Context-based strategy
LLM=Llama3
2026.03
79.3
Self-Debias
LLM=Mistral
2026.03
79.1
Context-based strategy
LLM=Gemma
2026.03
77
Self-Debias
LLM=Gemma
2026.03
76.9
Self-Debias
LLM=Llama3
2026.03
75.7
Zero-CoT
LLM=Gemma
2026.03
75.5
Zero-CoT
LLM=Llama3
2026.03
74
Feedback
Search any
task
Search any
task